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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19584
    Prev
    Next
    INDEX
    Explanations

    terms related to making changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to alterations or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç«
    -0.84
    ¯¯¯¯
    -0.78
    gerald
    -0.78
    stra
    -0.73
    vern
    -0.73
    mination
    -0.72
    äºĶ
    -0.72
    GE
    -0.70
    becue
    -0.69
    ¯¯
    -0.69
    POSITIVE LOGITS
    atile
    0.95
     effected
    0.84
    ivo
    0.76
    iations
    0.74
    itri
    0.72
    hyde
    0.72
    anwhile
    0.71
    jri
    0.71
    over
    0.70
    imedia
    0.68
    Activations Density 0.055%

    No Known Activations