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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    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. 6580
    Prev
    Next
    INDEX
    Explanations

    verbs that suggest defiance or resistance

    oai_token-act-pair · gpt-3.5-turbo

    expressions that convey resistance or challenge to authority or established norms

    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
    spot
    -0.80
    reau
    -0.76
    enary
    -0.75
    anamo
    -0.74
    istan
    -0.73
    onna
    -0.72
    aning
    -0.71
    uzzle
    -0.71
    eport
    -0.70
    owe
    -0.69
    POSITIVE LOGITS
     allegiance
    1.02
     precon
    0.98
     expectations
    0.94
     orthodoxy
    0.91
     gravity
    0.90
     belief
    0.89
     stereotypes
    0.87
     temptation
    0.85
     norms
    0.85
     tradition
    0.85
    Activations Density 0.272%

    No Known Activations