INDEX

Explanations

elements related to signs and visual representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ArrowToggle

-0.60

DeleteBehavior

-0.58

MemoryWarning

-0.55

ItemBackground

-0.54

OrNil

-0.50

リエーション

-0.50

setCellStyle

-0.50

octanol

-0.49

ereo

-0.48

 podstawie

-0.48

POSITIVE LOGITS

 saying

0.92

 proclaiming

0.87

 stating

0.81

 wording

0.78

 slogans

0.75

 proclaims

0.75

saying

0.75

 Saying

0.75

 labeled

0.74

 words

0.74

Activations Density 0.286%

elements related to signs and visual representations

No Comments

No Known Activations