INDEX

Explanations

numerical data related to experimental results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

зулта

-0.61

ukone

-0.55

 باخ

-0.55

ve

-0.55

estad

-0.54

InjectAttribute

-0.54

^^^^^^^^

-0.53

Galería

-0.53

roughs

-0.53

:]:

-0.52

POSITIVE LOGITS

1.00

########.

0.83

0.82

0.78

0.74

0.73

Activations Density 0.399%

numerical data related to experimental results

No Comments

No Known Activations