© 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. 7-RES-JB
    11. 17105
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or concepts starting with "Im" or "im"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Im" or its variations, indicating a focus on self-reference or personal statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -1.02
    ttes
    -0.77
     grapes
    -0.70
     wool
    -0.70
     stakes
    -0.69
     shroud
    -0.68
     braces
    -0.68
     Nazis
    -0.67
     Skydragon
    -0.67
     Chrys
    -0.66
    POSITIVE LOGITS
    mediate
    1.34
    mediately
    1.31
    perial
    1.29
    ply
    1.25
    perfect
    1.22
    ple
    1.22
    unity
    1.22
    posing
    1.19
    minent
    1.16
    medi
    1.15
    Activations Density 0.027%

    No Known Activations