© 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. 11-RES-JB
    11. 2691
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or situations where something specific happens or is required

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jug
    -0.67
    reads
    -0.66
    nih
    -0.65
    eting
    -0.64
    ãĤ©
    -0.62
    irlf
    -0.62
     cheers
    -0.58
    itamin
    -0.57
    nance
    -0.57
    stars
    -0.56
    POSITIVE LOGITS
     case
    2.50
     cases
    2.29
    case
    2.07
     Cases
    1.96
    cases
    1.86
     CASE
    1.68
    Case
    1.65
     Case
    1.63
     instances
    1.49
     circumstance
    1.44
    Activations Density 0.389%

    No Known Activations