© 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. 6-RES-JB
    11. 11758
    Prev
    Next
    INDEX
    Explanations

    references to materials something is made of

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing the materials or components that make up various objects

    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
    osponsors
    -1.02
    SPONSORED
    -0.88
    ahime
    -0.85
     challeng
    -0.80
     exting
    -0.80
    assi
    -0.78
     undermin
    -0.76
    isSpecialOrderable
    -0.76
    onential
    -0.74
    yip
    -0.72
    POSITIVE LOGITS
     scratch
    1.02
     clay
    0.83
     pure
    0.82
     fiber
    0.71
     tissue
    0.70
     Kan
    0.70
     cloth
    0.70
     recycled
    0.69
     Unreal
    0.66
     LEGO
    0.66
    Activations Density 0.116%

    No Known Activations