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. 335
    Prev
    Next
    INDEX
    Explanations

    sentences talking about future plans or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or conditionality

    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
    rities
    -0.66
     Alam
    -0.64
    plates
    -0.63
    ãĥ¼ãĥ³
    -0.61
    robe
    -0.61
    seys
    -0.60
    monds
    -0.59
    styles
    -0.59
     stripes
    -0.58
     lamps
    -0.58
    POSITIVE LOGITS
     blat
    0.79
     happen
    0.76
     happening
    0.75
     unintentional
    0.72
     happened
    0.70
     misunder
    0.70
    cture
    0.69
     happ
    0.68
    ebin
    0.68
     happens
    0.67
    Activations Density 0.205%

    No Known Activations