© 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. 1-RES-JB
    11. 2802
    Prev
    Next
    INDEX
    Explanations

    phrases or terms encapsulated in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and their associated textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.79
     Azerb
    -0.78
     rall
    -0.75
     accomp
    -0.74
     abduct
    -0.70
     inflic
    -0.70
     mete
    -0.69
     sacrific
    -0.68
     kidn
    -0.68
     Meteor
    -0.67
    POSITIVE LOGITS
    false
    1.19
    true
    1.11
    official
    1.11
    classic
    1.08
    too
    1.07
    almost
    1.06
    fair
    1.06
    little
    1.05
    every
    1.05
    green
    1.05
    Activations Density 0.148%

    No Known Activations