INDEX

Explanations

phrases related to various professions or roles

oai_token-act-pair · gpt-3.5-turbo

terms related to specific occupations or roles, including descriptors for people and objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

angan

-0.77

izoph

-0.67

°

-0.63

Scale

-0.61

ilion

-0.60

oho

-0.60

ĳ

-0.59

gall

-0.59

pless

-0.58

 elapsed

-0.58

POSITIVE LOGITS

 extraord

1.18

who

1.16

who

1.09

hood

1.02

 whom

1.01

doms

0.95

ship

0.95

gery

0.90

esses

0.89

dom

0.89

Activations Density 0.683%

phrases related to various professions or roles

terms related to specific occupations or roles, including descriptors for people and objects

No Comments

No Known Activations