© 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. 14908
    Prev
    Next
    INDEX
    Explanations

    adjectives describing quality or reliability

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey quality or reliability

    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
    hops
    -1.00
    lees
    -0.86
    aunts
    -0.84
    clips
    -0.82
    redients
    -0.81
    steps
    -0.81
    blocks
    -0.77
    ernels
    -0.77
    urches
    -0.76
    reports
    -0.76
    POSITIVE LOGITS
     solution
    1.02
     standpoint
    0.95
     foothold
    0.94
     relationship
    0.89
     person
    0.88
     environment
    0.88
     situation
    0.88
     dose
    0.87
     entity
    0.86
     approximation
    0.86
    Activations Density 0.398%

    No Known Activations