© 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. 23392
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "needed"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a requirement or necessity for something

    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
    ĪĴ
    -0.76
    claimer
    -0.70
    guyen
    -0.68
    gdala
    -0.66
    iple
    -0.65
    imore
    -0.63
    pret
    -0.63
    oller
    -0.62
    zees
    -0.61
    sheet
    -0.60
    POSITIVE LOGITS
     urgently
    0.91
    lessly
    0.79
     to
    0.76
     for
    0.73
     domestically
    0.66
     sshd
    0.65
     signatures
    0.63
    resso
    0.60
    ãĤĮ
    0.59
    ãģ®æ
    0.59
    Activations Density 0.040%

    No Known Activations