INDEX

Explanations

job titles and organizational positions

oai_token-act-pair · gpt-3.5-turbo

titles and positions of authority within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aples

-0.68

etheus

-0.66

grain

-0.65

utton

-0.65

[|

-0.65

akespeare

-0.64

 Caption

-0.64

 Newsp

-0.63

 oneself

-0.63

nder

-0.62

POSITIVE LOGITS

 counterpart

0.73

 negotiator

0.73

pport

0.70

 cousin

0.69

 advisor

0.68

 counterparts

0.66

ipal

0.65

 representative

0.65

 desk

0.65

agent

0.63

Activations Density 0.178%

job titles and organizational positions

titles and positions of authority within organizations

No Comments

No Known Activations