INDEX

Explanations

alphanumeric strings and specific identifiers related to programming or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

帖最后由

-0.78

mybatisplus

-0.64

StructEnd

-0.55

drawSprites

-0.55

AnchorStyles

-0.54

usercontent

-0.54

 BoxDecoration

-0.53

 rhestr

-0.52

photobucket

-0.51

mployment

-0.49

POSITIVE LOGITS

Efq

0.76

 myſelf

0.72

 Roskov

0.69

 itſelf

0.63

 Athenians

0.59

0.57

 raiſ

0.57

 subgoals

0.57

 unknownFields

0.56

Activations Density 0.048%

alphanumeric strings and specific identifiers related to programming or documentation

No Comments

No Known Activations