INDEX

Explanations

words related to professions or careers

oai_token-act-pair · gpt-3.5-turbo

terms related to various professions

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

arding

-0.68

 Meier

-0.65

Dub

-0.64

Oo

-0.61

 patches

-0.61

 deletion

-0.60

RR

-0.60

 straw

-0.58

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.58

intage

-0.58

POSITIVE LOGITS

ession

0.93

 Profession

0.84

 profession

0.83

ically

0.81

smanship

0.79

 association

0.76

ally

0.74

 ethic

0.73

iatric

0.73

iatrics

0.72

Activations Density 0.021%

words related to professions or careers

terms related to various professions

No Comments

No Known Activations