© 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. 10-RES-JB
    11. 6627
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and relational terms

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that are left in vulnerable or exposed situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haps
    -0.68
    wcsstore
    -0.63
     =>
    -0.61
    imum
    -0.60
    oho
    -0.60
    deals
    -0.59
     Encyclopedia
    -0.59
     confir
    -0.59
    idth
    -0.58
    afort
    -0.58
    POSITIVE LOGITS
     stranded
    1.24
     untouched
    1.24
     vulnerable
    1.16
     unprotected
    1.16
     powerless
    1.14
     alone
    1.12
     uninsured
    1.12
     unatt
    1.11
     dangling
    1.09
     intact
    1.09
    Activations Density 0.091%

    No Known Activations