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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 20188
    Prev
    Next
    INDEX
    Explanations

    terms related to governance, policies, and civil rights issues

    oai_token-act-pair · gpt-3.5-turbo

    topics related to crises and significant issues in society

    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
    anwhile
    -0.81
    ).[
    -0.72
    é¾įå
    -0.63
    %).
    -0.61
    ]."
    -0.60
     respectively
    -0.59
    )."
    -0.58
    }.
    -0.58
    ±
    -0.58
    initialized
    -0.57
    POSITIVE LOGITS
     ('
    0.62
     (#
    0.58
    âĦ¢:
    0.56
    !!!!!
    0.56
     bc
    0.56
     ($
    0.56
     sear
    0.55
     ðŁĻĤ
    0.55
    trip
    0.55
     (/
    0.54
    Activations Density 1.124%

    No Known Activations