INDEX

Explanations

references to occurrences or instances within a structured context, such as "block" or "level"

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

 payé

-0.79

%)$

-0.75

stdarg

-0.73

zczegól

-0.72

 musicales

-0.71

HttpFoundation

-0.71

Ory

-0.71

bå

-0.71

 sauvage

-0.70

Cuáles

-0.70

POSITIVE LOGITS

 BLOCK

1.98

 blocks

1.93

 Block

1.91

 block

1.88

block

1.86

BLOCK

1.85

 Blocks

1.83

Block

1.78

blocks

1.77

Blocks

1.65

Activations Density 0.037%

references to occurrences or instances within a structured context, such as "block" or "level"

No Comments

No Known Activations