© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 822
    Prev
    Next
    INDEX
    Explanations

    phrases related to the potential effects or impacts of various actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the impact or effect of actions or events

    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
     Leopard
    -0.66
    stan
    -0.65
    Stand
    -0.65
     spit
    -0.64
     Thrust
    -0.62
     mant
    -0.62
     SHE
    -0.61
     compet
    -0.60
     typed
    -0.59
     Brun
    -0.59
    POSITIVE LOGITS
     ripple
    1.11
    effects
    1.03
     reverber
    0.97
    lasting
    0.88
    Effects
    0.87
     consequential
    0.86
     impact
    0.85
     effects
    0.82
     multiplier
    0.80
     effect
    0.79
    Activations Density 0.289%

    No Known Activations