© 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. 957
    Prev
    Next
    INDEX
    Explanations

    questions and the auxiliary verb 'to be' in question form ('is' and 'are')

    oai_token-act-pair · gpt-4-turbo

    questions and statements related to defining or describing something

    oai_token-act-pair · gpt-3.5-turbo

    questions that seek clarification or definitions

    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
    gart
    -0.72
    hus
    -0.64
    mates
    -0.60
    tails
    -0.59
    hea
    -0.59
    gra
    -0.57
    jury
    -0.56
    ãĥĥ
    -0.55
    sha
    -0.54
     invitations
    -0.54
    POSITIVE LOGITS
    really
    0.87
     transpired
    0.76
    ?]
    0.74
     REALLY
    0.73
    urger
    0.70
    ?",
    0.69
    ?,
    0.68
    ?:
    0.67
     happened
    0.66
     wrought
    0.65
    Activations Density 0.883%

    No Known Activations