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. 3576
    Prev
    Next
    INDEX
    Explanations

    product descriptions and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or codes, particularly in reference to media content

    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
    )."
    -0.74
    .")
    -0.72
    ]."
    -0.66
     obsc
    -0.63
    opian
    -0.58
    ").
    -0.57
    '."
    -0.56
    });
    -0.56
    STDOUT
    -0.55
    Ire
    -0.55
    POSITIVE LOGITS
     âĵĺ
    0.73
     Originally
    0.71
     Released
    0.69
     ·
    0.68
     (?,
    0.66
     Featuring
    0.65
     |
    0.64
     Adds
    0.59
     Latest
    0.58
     Updated
    0.58
    Activations Density 0.959%

    No Known Activations