© 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. 4-RES-JB
    11. 14888
    Prev
    Next
    INDEX
    Explanations

    positive expressions or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or positivity towards a subject

    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
    pper
    -0.77
    ople
    -0.77
    eters
    -0.77
    iper
    -0.76
    hip
    -0.75
    Hop
    -0.73
    istan
    -0.71
    hod
    -0.70
    ratom
    -0.70
    ptin
    -0.66
    POSITIVE LOGITS
    enough
    1.30
     enough
    1.03
    reads
    0.96
     luck
    0.96
    sword
    0.92
    bye
    0.90
     Enough
    0.87
     intentions
    0.84
     karma
    0.84
     Samar
    0.83
    Activations Density 0.051%

    No Known Activations