© 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. 7-RES-JB
    11. 21409
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of bracketed content or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redu
    -0.75
     regression
    -0.70
     handlers
    -0.66
     ratios
    -0.66
     antioxid
    -0.65
     Elys
    -0.65
    ramid
    -0.64
     factories
    -0.64
    edIn
    -0.63
     deprivation
    -0.63
    POSITIVE LOGITS
    sic
    1.50
    ?]
    1.43
    !]
    1.36
    :]
    1.26
     edit
    1.16
    .]
    1.15
    ],
    1.14
    emphasis
    1.14
    ].
    1.14
    ](
    1.12
    Activations Density 0.038%

    No Known Activations