© 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. 8-RES-JB
    11. 18457
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching, exploring, or referring to specific information within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to exceptions or conditions related to specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yout
    -0.74
     freezes
    -0.72
    artifacts
    -0.72
    soDeliveryDate
    -0.71
     FANTASY
    -0.69
    anish
    -0.69
     MARK
    -0.68
    dos
    -0.67
    aza
    -0.66
     Solitaire
    -0.65
    POSITIVE LOGITS
    oyal
    0.75
     dearly
    0.70
    suff
    0.67
     reply
    0.67
     aspire
    0.65
     indebted
    0.65
     elector
    0.65
    ribut
    0.64
     allegiance
    0.63
     appl
    0.63
    Activations Density 0.171%

    No Known Activations