© 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. 9-RES-JB
    6. 13320
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that various government entities have taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or ownership by various subjects

    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
    Reading
    -0.66
    hesis
    -0.64
    Interested
    -0.61
    ribute
    -0.61
    ÃĹ
    -0.61
     IMAGES
    -0.61
    Else
    -0.60
    seless
    -0.57
     Pair
    -0.57
     Apart
    -0.56
    POSITIVE LOGITS
     been
    1.34
     vowed
    1.26
     begun
    1.15
     struggled
    1.14
     pledged
    1.14
     campaigned
    1.12
     repeatedly
    1.11
     insisted
    1.08
     urged
    1.07
     refused
    1.06
    Activations Density 0.231%

    No Known Activations