INDEX

Explanations

mentions of the reader in various contexts

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

WebElementEntity

-0.61

ArgsConstructor

-0.61

mybatisplus

-0.60

CompilerServices

-0.59

 traceback

-0.57

sham

-0.56

 samfun

-0.56

 leggen

-0.54

 MainAxisSize

-0.53

 ftate

-0.52

POSITIVE LOGITS

Inf

0.82

Inf

0.74

 suspects

0.72

 Reading

0.68

stris

0.66

setViewportView

0.66

 offenders

0.64

 respondents

0.64

ंदीखरीदारी

0.63

"]];

0.62

Activations Density 0.248%

mentions of the reader in various contexts

No Comments

No Known Activations