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. 9-RES-JB
    6. 15986
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code snippets containing specific variable names

    oai_token-act-pair · gpt-3.5-turbo

    code elements and structures related to functions and variables in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconc
    -0.88
    wcs
    -0.75
     reconciliation
    -0.69
     ACTIONS
    -0.65
    EVA
    -0.64
     assurance
    -0.64
    international
    -0.64
    cellaneous
    -0.64
    ournal
    -0.62
    packing
    -0.62
    POSITIVE LOGITS
    }
    2.11
    }}
    2.05
    }}}
    2.03
    })
    1.90
    }"
    1.81
    }\
    1.73
    },
    1.68
    }{
    1.67
    }.
    1.58
     }}
    1.54
    Activations Density 0.054%

    No Known Activations