© 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. 2-RES-JB
    11. 24024
    Prev
    Next
    INDEX
    Explanations

    words related to filters or filtering

    oai_token-act-pair · gpt-3.5-turbo

    references to filtering mechanisms or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eanor
    -0.78
    nee
    -0.77
    DAY
    -0.69
    pered
    -0.68
    olars
    -0.68
    retch
    -0.66
    erald
    -0.66
    eworld
    -0.64
    NAS
    -0.63
    AAAAAAAA
    -0.63
    POSITIVE LOGITS
     filters
    1.04
     filtering
    1.03
     filter
    0.98
     Filter
    0.93
    filter
    0.86
     cleaners
    0.83
     cutoff
    0.81
     pores
    0.80
     filtered
    0.77
     capacitor
    0.73
    Activations Density 0.013%

    No Known Activations