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. 15847
    Prev
    Next
    INDEX
    Explanations

    references to the media outlet "IGN"

    oai_token-act-pair · gpt-3.5-turbo

    references to the media outlet IGN

    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
     Georgian
    -0.77
    zynski
    -0.75
    foot
    -0.73
    xual
    -0.70
    tons
    -0.70
     Finnish
    -0.69
    kees
    -0.69
    annis
    -0.69
     Eston
    -0.67
     Azerbai
    -0.66
    POSITIVE LOGITS
    VERTISEMENT
    0.98
    ORED
    0.97
    ITION
    0.96
     IGN
    0.90
    uable
    0.85
    ORE
    0.84
    ution
    0.84
    ITE
    0.83
    IFIED
    0.82
    ibly
    0.81
    Activations Density 0.014%

    No Known Activations