INDEX

Explanations

expressions related to impressions and perceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 otomatig

-0.71

 AssemblyCulture

-0.63

öhn

-0.60

 restTemplate

-0.57

 Akismet

-0.57

IndentedString

-0.56

acterium

-0.55

}))

-0.55

stdc

-0.54

 endregion

-0.53

POSITIVE LOGITS

Proto

0.76

 Proto

0.75

 http

0.69

 proto

0.66

 aDecoder

0.61

 ujednoznacz

0.60

proto

0.59

 PROTO

0.59

xuan

0.58

PROTO

0.57

Activations Density 0.085%

expressions related to impressions and perceptions

No Comments

No Known Activations