© 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. 3-RES-JB
    11. 14759
    Prev
    Next
    INDEX
    Explanations

    mentions of qualifications or attributes indicating expertise or permission

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "credentials" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mast
    -0.73
    Bed
    -0.68
     Bed
    -0.67
    child
    -0.63
     Depression
    -0.62
    upon
    -0.60
    alter
    -0.59
    hearted
    -0.59
     Mald
    -0.59
     Barg
    -0.58
    POSITIVE LOGITS
     credentials
    1.52
     credential
    0.94
    milo
    0.83
     certs
    0.81
     qualifications
    0.79
     holders
    0.77
     badges
    0.76
     certificates
    0.73
     pedigree
    0.71
     holder
    0.70
    Activations Density 0.007%

    No Known Activations