© 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. 23393
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions being performed or applied

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the action of placing or assigning something

    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
     Grounds
    -0.63
    externalActionCode
    -0.58
     LOVE
    -0.56
     remnant
    -0.55
     resemblance
    -0.54
     Voices
    -0.54
    CHAT
    -0.54
    Flight
    -0.53
     stripe
    -0.53
     corridors
    -0.53
    POSITIVE LOGITS
    tering
    1.03
    tin
    1.02
    ongh
    0.93
     together
    0.92
    rid
    0.90
    arnaev
    0.88
    ative
    0.88
    TING
    0.86
    downs
    0.86
    job
    0.85
    Activations Density 0.048%

    No Known Activations