INDEX

Explanations

references to exclusion or differentiation in context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hasMany

-0.45

‘

-0.44

nya

-0.43

 about

-0.42

 Schulte

-0.42

==

-0.41

 modern

-0.41

II

-0.41

’

-0.40

POSITIVE LOGITS

findpost

0.98

tagHelperRunner

0.98

 '\\;'

0.95

VersionUID

0.92

ftagPool

0.91

Rè

0.86

LEncoder

0.84

NewUrlParser

0.83

UnusedPrivate

0.83

 propOrder

0.82

Activations Density 0.367%

references to exclusion or differentiation in context

No Comments

No Known Activations