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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18934
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative experiences or criticism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional and physical distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.74
    FN
    -0.63
    cyclop
    -0.61
    sonian
    -0.57
     renovated
    -0.57
    assadors
    -0.54
     Negro
    -0.53
     Schwar
    -0.53
    çīĪ
    -0.53
    inois
    -0.53
    POSITIVE LOGITS
     otherwise
    0.63
     contagious
    0.59
    effic
    0.58
     latent
    0.57
     inflicted
    0.56
     bodily
    0.56
     stemming
    0.56
     ego
    0.55
     PTSD
    0.54
     plag
    0.54
    Activations Density 2.105%

    No Known Activations