© 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. 8-RES-JB
    11. 18470
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of availability or accessibility

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and adjectives related to modes of availability and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Payne
    -0.69
    arella
    -0.69
     Tools
    -0.66
     Timbers
    -0.64
    ydia
    -0.64
     Rory
    -0.64
    oria
    -0.64
    oleon
    -0.63
     Majority
    -0.62
     Hardware
    -0.62
    POSITIVE LOGITS
     spaced
    0.92
     occurring
    0.86
     constructed
    0.84
    existing
    0.84
    protected
    0.82
     identifiable
    0.81
     vaccinated
    0.81
     formulated
    0.81
     veiled
    0.80
    encrypted
    0.80
    Activations Density 0.193%

    No Known Activations