© 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. 9-RES-JB
    11. 18009
    Prev
    Next
    INDEX
    Explanations

    people or entities that have undergone a change in their status, role, or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating current status or condition of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initially
    -0.73
     originally
    -0.72
     always
    -0.70
     earlier
    -0.68
    orig
    -0.67
     lately
    -0.66
     beforehand
    -0.65
     meantime
    -0.63
    later
    -0.63
     yesterday
    -0.61
    POSITIVE LOGITS
    Reviewer
    0.78
    YL
    0.72
    hops
    0.70
    roxy
    0.68
    adian
    0.67
    Ô
    0.67
    YP
    0.66
    enium
    0.66
    ģĸ
    0.65
    aukee
    0.65
    Activations Density 0.367%

    No Known Activations