© 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. 9189
    Prev
    Next
    INDEX
    Explanations

    words related to different seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of seasons

    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
    hai
    -0.79
    aware
    -0.69
    plete
    -0.66
    cart
    -0.63
     sten
    -0.60
     reim
    -0.60
     plugged
    -0.59
    tap
    -0.58
    mercial
    -0.58
    enei
    -0.57
    POSITIVE LOGITS
    ally
    0.92
     opener
    0.85
     finale
    0.84
     premiere
    0.78
     Afric
    0.70
    igraph
    0.68
    ings
    0.68
    ticket
    0.67
    é¾
    0.65
    ality
    0.65
    Activations Density 0.035%

    No Known Activations