© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11229
    Prev
    Next
    INDEX
    Explanations

    words related to intense, extreme, or strong situations or emotions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with advertisements and intense activities or emotions

    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
    Sensor
    -0.85
    »Ĵ
    -0.75
    ropy
    -0.72
     Pinball
    -0.68
     Supervisor
    -0.67
     Rez
    -0.67
    elia
    -0.66
    arers
    -0.64
    IDA
    -0.64
    itu
    -0.63
    POSITIVE LOGITS
    culosis
    1.16
    draft
    0.87
    geoning
    0.76
    heit
    0.76
    umbers
    0.75
    advertisement
    0.71
    itatively
    0.69
    æł
    0.69
     Bagg
    0.68
    20439
    0.68
    Activations Density 0.027%

    No Known Activations