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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 2455
    Prev
    Next
    INDEX
    Explanations

    code snippets and errors related to programming

    oai_token-act-pair · gpt-3.5-turbo

    programming syntax elements related to functions and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.79
    shaw
    -0.67
    ring
    -0.65
     marqu
    -0.65
     Nanto
    -0.63
    ening
    -0.63
    azing
    -0.61
    ikuman
    -0.60
     Primal
    -0.59
     conven
    -0.59
    POSITIVE LOGITS
    vim
    0.87
    }}
    0.81
    english
    0.78
    }
    0.75
     //
    0.75
    uration
    0.75
    />
    0.73
     Âł Âł Âł Âł
    0.73
    //
    0.73
    $$
    0.71
    Activations Density 0.027%

    No Known Activations