© 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. 9-RES-JB
    11. 4713
    Prev
    Next
    INDEX
    Explanations

    companies or individuals that have been contacted or reached out to

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to timeframes and periodic occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.89
     volcan
    -0.71
     mobs
    -0.69
     paradise
    -0.68
     oneself
    -0.65
     Conserv
    -0.63
     idols
    -0.61
     perish
    -0.60
    Die
    -0.60
     mun
    -0.60
    POSITIVE LOGITS
     requesting
    1.22
     asking
    1.08
     informing
    1.06
     regarding
    0.93
     advising
    0.92
     alleging
    0.91
     inqu
    0.89
     confirming
    0.88
     urging
    0.88
     seeking
    0.85
    Activations Density 0.464%

    No Known Activations