INDEX

Explanations

phrases related to reputation

oai_token-act-pair · gpt-3.5-turbo

references to reputation and its varying degrees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pheus

-0.79

tein

-0.75

oop

-0.70

chedel

-0.70

sight

-0.69

onal

-0.68

nes

-0.67

WARE

-0.64

ECK

-0.64

shows

-0.62

POSITIVE LOGITS

 tarn

0.95

 reputation

0.94

 abroad

0.88

 internationally

0.86

worthiness

0.82

 bearer

0.80

 amongst

0.80

 forged

0.79

 preced

0.78

 bestowed

0.78

Activations Density 0.072%

phrases related to reputation

references to reputation and its varying degrees

No Comments

No Known Activations