© 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. 2-RES-JB
    6. 4023
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or written exchanges

    oai_token-act-pair · gpt-3.5-turbo

    references to correspondence and communications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bold
    -0.85
    itar
    -0.80
    asted
    -0.80
    rug
    -0.78
    bern
    -0.77
    oult
    -0.77
    jam
    -0.73
    ofi
    -0.71
     Cities
    -0.71
    gets
    -0.70
    POSITIVE LOGITS
     correspondence
    1.22
     dealings
    0.98
     bidder
    0.88
    DragonMagazine
    0.87
     paperwork
    0.85
     handlers
    0.84
    ulty
    0.83
     tracing
    0.83
     irregularities
    0.83
    dayName
    0.80
    Activations Density 0.014%

    No Known Activations