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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 23578
    Prev
    Next
    INDEX
    Explanations

    terms related to verifying and confirming information

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating verifiability or proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Towns
    -0.66
     Franks
    -0.66
     cooker
    -0.65
    emi
    -0.65
    NetMessage
    -0.63
     Turks
    -0.62
     flyers
    -0.62
    »Ĵ
    -0.62
     Fever
    -0.59
     Pearce
    -0.59
    POSITIVE LOGITS
    ifiable
    1.23
    itable
    1.20
    ulent
    1.07
    istically
    1.05
    itably
    1.05
    bat
    1.02
    bly
    0.89
    ific
    0.89
    bling
    0.89
    anda
    0.89
    Activations Density 0.020%

    No Known Activations