© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10915
    Prev
    Next
    INDEX
    Explanations

    names containing special characters

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity, likely related to urban areas or specific neighborhoods

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

    No Comments

    Negative Logits
     Bagg
    -0.75
     Crown
    -0.73
    hibited
    -0.72
    querque
    -0.72
     Bloom
    -0.71
    ographed
    -0.68
     Lomb
    -0.67
    verett
    -0.67
     NV
    -0.67
     Weiner
    -0.66
    POSITIVE LOGITS
    istors
    0.75
    terday
    0.72
    eners
    0.70
    idious
    0.70
    ruction
    0.69
    ionic
    0.68
    pter
    0.68
    isp
    0.67
    irez
    0.67
    ions
    0.67
    Activations Density 0.022%

    No Known Activations