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. 10-RES-JB
    6. 17206
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or tasks to be done

    oai_token-act-pair · gpt-3.5-turbo

    themes related to need and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.57
    oult
    -0.55
    selves
    -0.54
    ashtra
    -0.53
    schild
    -0.51
    nai
    -0.51
    chy
    -0.49
     withd
    -0.48
    word
    -0.47
    omb
    -0.47
    POSITIVE LOGITS
     it
    1.72
     them
    1.53
     thereof
    1.46
     hers
    1.16
     thereto
    1.15
     therein
    1.13
     Them
    1.10
     theirs
    1.10
     THEM
    1.07
    them
    1.04
    Activations Density 1.626%

    No Known Activations