© 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. 11-RES-JB
    11. 760
    Prev
    Next
    INDEX
    Explanations

    higher education institutions, specifically universities and colleges

    oai_token-act-pair · gpt-3.5-turbo

    names of educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ich
    -0.92
     Kak
    -0.82
     Kitt
    -0.80
     Esper
    -0.79
     Amit
    -0.78
     Kom
    -0.76
     Mach
    -0.75
     Konami
    -0.75
    Haw
    -0.73
     Ak
    -0.72
    POSITIVE LOGITS
    R
    1.39
    r
    1.36
    Rs
    1.34
    RR
    1.29
    RB
    1.24
    RC
    1.23
    rs
    1.22
    RD
    1.20
    rg
    1.20
    RI
    1.20
    Activations Density 1.001%

    No Known Activations