© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 960
    Prev
    Next
    INDEX
    Explanations

    phrases with the word 'he' followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Joint
    -0.62
     Claire
    -0.62
     Pwr
    -0.62
     Transactions
    -0.62
     Pastebin
    -0.61
    aj
    -0.60
     Columb
    -0.60
     Girls
    -0.59
     Engineers
    -0.59
     Bearing
    -0.58
    POSITIVE LOGITS
    'd
    1.11
    eded
    1.08
    'll
    1.07
    zbollah
    0.97
     redes
    0.87
     encount
    0.84
    pherd
    0.82
    resy
    0.80
    aven
    0.79
    athered
    0.79
    Activations Density 0.249%

    No Known Activations