© 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. 11149
    Prev
    Next
    INDEX
    Explanations

    hands

    oai_token-act-pair · gpt-3.5-turbo

    the term "ands" and its variations in various contexts

    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
    ded
    -0.66
    STON
    -0.65
    thia
    -0.60
    UTION
    -0.60
     nerv
    -0.58
     Correction
    -0.57
    versely
    -0.57
    culus
    -0.56
    mph
    -0.56
     Kills
    -0.56
    POSITIVE LOGITS
    ands
    1.36
    anding
    1.12
    anded
    1.10
    lash
    0.89
    ynski
    0.87
    itute
    0.82
    indal
    0.82
    chwitz
    0.81
    rums
    0.81
    =]
    0.80
    Activations Density 0.007%

    No Known Activations