© 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. 7123
    Prev
    Next
    INDEX
    Explanations

    phrases containing words related to influence or interaction with others

    oai_token-act-pair · gpt-3.5-turbo

    references to a collective group or community involvement

    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
    Tour
    -0.68
    ctor
    -0.65
    Url
    -0.64
    plex
    -0.63
    ISTER
    -0.62
    itation
    -0.62
    Mail
    -0.62
    ihara
    -0.61
    Flight
    -0.60
    ister
    -0.60
    POSITIVE LOGITS
    cius
    0.95
    worldly
    0.92
     behavi
    0.83
    ĸļ
    0.80
     indo
    0.78
    ktop
    0.77
    soType
    0.77
     challeng
    0.77
    ngth
    0.74
     describ
    0.73
    Activations Density 0.025%

    No Known Activations