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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 14026
    Prev
    Next
    INDEX
    Explanations

    succinct summaries or explanations

    oai_token-act-pair · gpt-3.5-turbo

    summaries or paraphrases of information

    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
    20439
    -1.01
    ennial
    -0.71
    ocene
    -0.71
    iger
    -0.70
    enary
    -0.67
    psey
    -0.65
     grandchildren
    -0.65
    aily
    -0.64
    rils
    -0.64
    arsity
    -0.63
    POSITIVE LOGITS
     nutshell
    1.05
     Basically
    0.78
     Meaning
    0.77
    Basically
    0.75
     Essentially
    0.74
     CoC
    0.72
     Saying
    0.68
     ¯
    0.68
     thats
    0.67
    ãĤª
    0.67
    Activations Density 0.063%

    No Known Activations