INDEX

Explanations

names of individuals and organizations involved in research or acknowledgment sections of academic texts

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

 Monfieur

-0.86

Efq

-0.85

 Diſ

-0.84

 Theſe

-0.83

 Houſe

-0.82

 ſche

-0.80

 Anſ

-0.79

Eſ

-0.79

 ſtate

-0.79

 perſon

-0.78

POSITIVE LOGITS

RenderAtEndOf

0.78

 EconPapers

0.66

RectangleBorder

0.62

 consultato

0.61

InjectAttribute

0.59

WriteBarrier

0.59

 defaultstate

0.57

complexContent

0.56

PreExecute

0.56

CrossOrigin

0.54

Activations Density 0.277%

names of individuals and organizations involved in research or acknowledgment sections of academic texts

No Comments

No Known Activations