© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3341
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to stages, phases, or milestones in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Firstly
    -0.58
    ãĤ¦ãĤ¹
    -0.54
    ãĤ´ãĥ³
    -0.53
    channelAvailability
    -0.52
    Shape
    -0.51
    rawdownloadcloneembedreportprint
    -0.49
    NAS
    -0.49
    iquette
    -0.48
    ãĥ¼ãĥĨãĤ£
    -0.48
     Canaver
    -0.48
    POSITIVE LOGITS
    ]).
    0.50
    .")
    0.47
    .'"
    0.47
    ]."
    0.44
    ).[
    0.44
    ];
    0.43
     weak
    0.43
     undercut
    0.41
     bonding
    0.41
     [(
    0.41
    Activations Density 3.682%

    No Known Activations