INDEX

Explanations

sentences describing loss or defeat

oai_token-act-pair · gpt-3.5-turbo

articles, specifically the words "a" and "an"

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

grounds

-0.81

 intentions

-0.72

 arrangements

-0.70

 factors

-0.69

evidence

-0.66

mods

-0.64

Edit

-0.64

SPONSORED

-0.63

Allow

-0.63

external

-0.63

POSITIVE LOGITS

 bunch

1.21

 handful

1.15

lot

1.10

 couple

1.03

 sizeable

1.00

 sizable

0.99

few

0.99

 dozen

0.98

 whopping

0.98

 portion

0.96

Activations Density 0.282%

sentences describing loss or defeat

articles, specifically the words "a" and "an"

No Comments

No Known Activations