© 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. 18586
    Prev
    Next
    INDEX
    Explanations

    direct quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and direct speech in text

    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
     nod
    -0.69
     lair
    -0.63
     nodd
    -0.62
     rundown
    -0.61
     fray
    -0.61
     salute
    -0.60
     Versus
    -0.60
     alias
    -0.58
     playbook
    -0.57
    lled
    -0.57
    POSITIVE LOGITS
    there
    1.27
    nob
    1.15
    they
    1.06
    someone
    1.05
    everyone
    1.02
    these
    1.01
    many
    1.01
    when
    0.94
    every
    0.93
    despite
    0.91
    Activations Density 0.217%

    No Known Activations