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. 3742
    Prev
    Next
    INDEX
    Explanations

    terms related to racial identity and classification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to race and ethnicity

    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
     Dolphin
    -0.70
     omission
    -0.70
     Painter
    -0.70
    ĸļ
    -0.69
     Rabbit
    -0.69
     Pub
    -0.65
     Isles
    -0.65
     ABE
    -0.65
     IMAGES
    -0.65
     Carnival
    -0.64
    POSITIVE LOGITS
    onder
    0.86
    GHz
    0.85
    ound
    0.83
    ield
    0.83
    atri
    0.83
    llular
    0.82
    imensional
    0.82
    atures
    0.82
    rop
    0.80
    ucle
    0.79
    Activations Density 0.072%

    No Known Activations