© 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. 23649
    Prev
    Next
    INDEX
    Explanations

    words related to preventative actions or measures

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of effects or conditions, particularly focusing on descriptors in scientific or medical contexts

    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
    owship
    -0.91
    jri
    -0.80
    stead
    -0.79
    eem
    -0.79
    igon
    -0.78
    olicited
    -0.78
    ufact
    -0.77
    pins
    -0.76
    igrate
    -0.76
    omet
    -0.74
    POSITIVE LOGITS
     measures
    0.86
     Measures
    0.86
     pronoun
    0.80
     minded
    0.77
     easing
    0.76
     mechanism
    0.74
     injunction
    0.74
     effect
    0.74
     tendencies
    0.73
     Bastard
    0.72
    Activations Density 0.148%

    No Known Activations