Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11929
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being specifically left to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of delegation or leaving decisions to others

    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
    interstitial
    -0.70
    abilia
    -0.65
    started
    -0.65
    enos
    -0.63
    caster
    -0.63
    lifting
    -0.62
    named
    -0.62
     Started
    -0.61
     billed
    -0.61
    sounding
    -0.60
    POSITIVE LOGITS
     fend
    1.15
     explore
    0.84
     Beaver
    0.84
     roam
    0.78
     wander
    0.76
     pasture
    0.75
     rot
    0.72
     improv
    0.71
     determine
    0.70
    pless
    0.70
    Activations Density 0.071%

    No Known Activations