© 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. 0-RES-JB
    11. 16997
    Prev
    Next
    INDEX
    Explanations

    words related to enclosures or protective barriers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to encampment or enclosure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urga
    -0.71
    care
    -0.70
     Trend
    -0.69
     Career
    -0.69
     hindsight
    -0.66
    forums
    -0.66
     Gay
    -0.65
    IER
    -0.64
    Journal
    -0.64
     Tasmania
    -0.64
    POSITIVE LOGITS
     enc
    3.97
    enc
    1.60
     encoding
    1.45
     Enc
    1.38
    Enc
    1.36
     envelop
    1.36
     encl
    1.32
     encode
    1.28
     delim
    1.21
     encoded
    1.18
    Activations Density 0.017%

    No Known Activations