INDEX

Explanations

mentions of offsets in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.91

氓

-0.83

:✨

-0.82

 Freire

-0.77

 resourceCulture

-0.76

rinfo

-0.75

Vidite

-0.74

 RequestMethod

-0.73

Ath

-0.72

 køb

-0.70

POSITIVE LOGITS

 Abbe

0.87

enment

0.86

tling

0.84

ting

0.83

tlement

0.78

 Treff

0.76

cknow

0.74

 offset

0.74

teis

0.68

iomanip

0.68

Activations Density 0.187%

mentions of offsets in various contexts

No Comments

No Known Activations