© 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. 1-RES-JB
    11. 3262
    Prev
    Next
    INDEX
    Explanations

    phrases related to potentially difficult or dangerous scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to various situations that arise in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roe
    -0.83
    rotein
    -0.72
    rik
    -0.70
    uster
    -0.69
    rib
    -0.68
    sub
    -0.66
    rica
    -0.65
    rium
    -0.64
     Bones
    -0.63
    head
    -0.63
    POSITIVE LOGITS
     situations
    1.32
    uations
    1.10
     scenarios
    1.06
     Situation
    0.95
     circumstances
    0.94
     predic
    0.89
    afety
    0.85
     situation
    0.85
     involving
    0.82
     contexts
    0.78
    Activations Density 0.010%

    No Known Activations