© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 2443
    Prev
    Next
    INDEX
    Explanations

    phrases related to file management or coding, such as file formats and manipulation commands

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pos" and its variations, indicating it is focused on identifying a specific term or concept related to positioning or positivity within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loo
    -0.76
    doms
    -0.73
    ãģ®éŃĶ
    -0.68
     casc
    -0.65
     oats
    -0.60
     fronts
    -0.60
     British
    -0.59
    ibaba
    -0.59
     Jazeera
    -0.59
     diminishing
    -0.58
    POSITIVE LOGITS
    itory
    1.31
    pos
    1.22
    itions
    1.11
    itional
    1.05
    itives
    1.04
    itor
    1.00
    idon
    0.96
    xual
    0.96
    position
    0.94
    itiveness
    0.92
    Activations Density 0.005%

    No Known Activations