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. 4449
    Prev
    Next
    INDEX
    Explanations

    short descriptions or details about different topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that detail rankings or statistics related to various subjects

    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
    orer
    -0.63
    ARCH
    -0.61
    mouth
    -0.61
     Gw
    -0.59
    OND
    -0.58
    URE
    -0.57
    oner
    -0.57
    Deploy
    -0.56
    ¶ħ
    -0.56
    ORE
    -0.55
    POSITIVE LOGITS
     respectively
    0.90
     albeit
    0.77
    ]).
    0.76
    )).
    0.76
     etc
    0.73
    ]),
    0.72
    FontSize
    0.71
    })
    0.70
    }"
    0.68
    )))
    0.67
    Activations Density 0.571%

    No Known Activations