© 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. 18603
    Prev
    Next
    INDEX
    Explanations

    descriptions of events or incidents mentioned in articles

    oai_token-act-pair · gpt-3.5-turbo

    references to academic articles and publications

    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
    tsy
    -0.75
     accommodation
    -0.72
    Cooldown
    -0.65
     toast
    -0.65
    ah
    -0.63
     drains
    -0.61
    ahs
    -0.61
     obe
    -0.60
    ime
    -0.59
     reperto
    -0.58
    POSITIVE LOGITS
     titled
    1.09
     headlined
    1.07
    vertisement
    1.03
    uggest
    1.01
    lished
    0.93
    itled
    0.91
     purported
    0.85
     authored
    0.85
     published
    0.85
     entitled
    0.84
    Activations Density 0.384%

    No Known Activations