INDEX

Explanations

negative connotations or implications related to specific topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.64

-0.61

EndContext

-0.58

-0.56

 serializers

-0.56

-0.54

-0.52

autoreleasepool

-0.51

POSITIVE LOGITS

$_"

0.94

 raiſ

0.89

based

0.88

related

0.87

Efq

0.87

+#+#

0.84

 related

0.84

 giuri

0.83

saurus

0.82

 based

0.82

Activations Density 0.385%

negative connotations or implications related to specific topics

No Comments

No Known Activations