© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 12144
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental degradation, particularly deforestation in the Amazon rainforest

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of square brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intellig
    -0.73
    wagen
    -0.69
     estim
    -0.69
     piping
    -0.69
     poisoning
    -0.68
     appreci
    -0.68
     swe
    -0.67
     cones
    -0.67
     explan
    -0.67
     surrogate
    -0.67
    POSITIVE LOGITS
    ...]
    1.57
    âĢ¦]
    1.57
    Pg
    1.26
    !]
    1.24
    ?]
    1.10
    ](
    1.06
    Laughs
    1.06
    paragraph
    1.05
    actionDate
    1.01
    REDACTED
    1.00
    Activations Density 0.019%

    No Known Activations