© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 5088
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks being done or actions being carried out by someone or something

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions related to tasks and responsibilities

    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
     encount
    -0.69
    76561
    -0.67
    é¾įå
    -0.62
     compan
    -0.57
     opio
    -0.57
     forgetting
    -0.56
     Dating
    -0.56
     forbids
    -0.56
    illon
    -0.55
     shalt
    -0.55
    POSITIVE LOGITS
    able
    0.98
     theirs
    0.92
    ingly
    0.87
    ables
    0.82
    tion
    0.80
    heed
    0.79
    estyle
    0.79
    ership
    0.79
    ible
    0.77
    vind
    0.77
    Activations Density 0.234%

    No Known Activations