INDEX

Explanations

elements of a structured list or sequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Solubility

-0.44

’

-0.42

uss

-0.41

â

-0.41

盛

-0.41

 урна

-0.41

tk

-0.41

ver

-0.41

do

-0.41

 sfor

-0.40

POSITIVE LOGITS

expandindo

0.89



0.88

 snippetHide

0.78

Datuak

0.77

Abitanti

0.73

featureID

0.73

Personendaten

0.72

WriteBarrier

0.70

antaranya

0.68

ArrowToggle

0.68

Activations Density 0.636%

elements of a structured list or sequence

No Comments

No Known Activations