© 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. 1-RES-JB
    11. 20703
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of identity

    oai_token-act-pair · gpt-3.5-turbo

    references to identity, particularly in relation to social, legal, and personal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.67
    baugh
    -0.66
    âķIJâķIJ
    -0.66
     Vaj
    -0.65
    amps
    -0.64
    oys
    -0.63
    paid
    -0.63
    ש
    -0.62
    ithing
    -0.60
     spare
    -0.60
    POSITIVE LOGITS
     identity
    1.12
     identities
    1.02
     Identity
    1.00
     è£ıè
    0.93
    entity
    0.87
    iosyncr
    0.84
    ativity
    0.81
    leck
    0.78
    holder
    0.78
     Leilan
    0.76
    Activations Density 0.010%

    No Known Activations