© 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. 7-RES-JB
    11. 13391
    Prev
    Next
    INDEX
    Explanations

    opinions or discussions about what is considered appropriate or suitable in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chet
    -0.85
    gets
    -0.78
    planes
    -0.76
    plane
    -0.74
    urger
    -0.71
    herer
    -0.71
    cipl
    -0.70
    glass
    -0.68
    peak
    -0.67
    quad
    -0.66
    POSITIVE LOGITS
    appropriate
    0.82
    tarian
    0.82
     circumstances
    0.80
     sized
    0.79
     attire
    0.77
     responses
    0.77
     behaviour
    0.76
     punishment
    0.76
     amounts
    0.75
     pronouns
    0.75
    Activations Density 0.029%

    No Known Activations