INDEX

Explanations

words related to writing and bargaining

oai_token-act-pair · gpt-3.5-turbo

references to writing or written content

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

 vain

-0.64

 Idaho

-0.64

 Scotia

-0.63

 Peninsula

-0.63

 motto

-0.63

 Bravo

-0.63

odor

-0.62

ware

-0.62

 Hale

-0.61

 eldest

-0.61

POSITIVE LOGITS

es

1.21

terness

0.97

esh

0.94

hest

0.93

awa

0.93

ecake

0.93

hes

0.92

hou

0.88

egu

0.88

emen

0.87

Activations Density 0.033%

words related to writing and bargaining

references to writing or written content

No Comments

No Known Activations