© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1056
    Prev
    Next
    INDEX
    Explanations

    mentions of the increasing prevalence of a phenomenon or trend

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to increasing trends and concerns in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beforehand
    -0.71
     1922
    -0.70
     damned
    -0.70
     1919
    -0.70
     1935
    -0.69
     1938
    -0.68
     Gord
    -0.67
     longest
    -0.66
     1916
    -0.66
     Shame
    -0.65
    POSITIVE LOGITS
     increasingly
    0.89
     smartphones
    0.82
     automation
    0.81
     specialization
    0.79
    ersive
    0.79
    catentry
    0.77
    ibaba
    0.77
    Demand
    0.75
    NetMessage
    0.73
     realizing
    0.73
    Activations Density 0.766%

    No Known Activations