© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to significant events or activities

    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
    lio
    -0.58
    tan
    -0.57
    yond
    -0.56
    been
    -0.56
    thur
    -0.55
    thin
    -0.55
    illion
    -0.55
    inner
    -0.55
    iversary
    -0.55
    ised
    -0.53
    POSITIVE LOGITS
    Ĥİ
    0.67
     tremend
    0.59
     AAP
    0.58
    hement
    0.56
    ĵĺ
    0.54
     showc
    0.53
     Pike
    0.52
     unsuccessfully
    0.51
     bows
    0.50
     briefly
    0.50
    Activations Density 1.308%

    No Known Activations