INDEX

Explanations

mentions of job-related terms and concepts

oai_token-act-pair · gpt-3.5-turbo

references to job creation and employment statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Revision

-0.74

yx

-0.74

theless

-0.68

 Flavoring

-0.63

 curv

-0.63

Oo

-0.60

 Totem

-0.60

gran

-0.59

Alpha

-0.59

 Qing

-0.59

POSITIVE LOGITS

 jobs

0.93

jobs

0.83

anooga

0.82

uilt

0.79

Builder

0.78

inders

0.77

essions

0.76

 Jobs

0.75

riet

0.73

lif

0.71

Activations Density 0.039%

mentions of job-related terms and concepts

references to job creation and employment statistics

No Comments

No Known Activations