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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9-RES-JB
    6. 1969
    Prev
    Next
    INDEX
    Explanations

    The neuron seems to be looking for specific proper nouns and names, such as political figures, locations, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent political figures and groups

    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
     Barnett
    -0.69
    ãĥ´ãĤ¡
    -0.68
    oslav
    -0.64
    é¾
    -0.58
    icians
    -0.57
    shed
    -0.55
     pse
    -0.54
     democrat
    -0.54
     denomin
    -0.54
    ribes
    -0.54
    POSITIVE LOGITS
    themed
    0.79
     burial
    0.69
    abilia
    0.67
     headquartered
    0.67
     attend
    0.66
    Jr
    0.62
     greeting
    0.62
     overseas
    0.60
     themed
    0.60
     reside
    0.60
    Activations Density 0.662%

    No Known Activations