INDEX

Explanations

sequences of tabs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<bos>

-0.84

MergeFrom

-0.82

enterOuterAlt

-0.80

Izvori

-0.79

Jeografia

-0.78

帖最后由

-0.76

 &___

-0.76

rmtree

-0.75

oredCriteria

-0.74

Diwedd

-0.69

POSITIVE LOGITS

 متعلقه

0.74

 Majefty

0.54

inguém

0.54

 Ganes

0.53

éndolo

0.52

SNA

0.52

0.51

uxxxx

0.51

 glau

0.51

Activations Density 0.008%

sequences of tabs

No Comments

No Known Activations