INDEX

Explanations

references to the source or origin of something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "from" in various contexts

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

hirt

-0.86

olson

-0.79

leneck

-0.78

hon

-0.76

Mask

-0.75

merce

-0.73

osen

-0.73

ername

-0.73

scientific

-0.72

stakes

-0.72

POSITIVE LOGITS

 afar

1.18

 abroad

1.00

 scratch

0.82

 whence

0.81

 Fukushima

0.79

 Corpus

0.78

 thence

0.76

 inside

0.72

 neighboring

0.71

 neighbouring

0.69

Activations Density 0.120%

references to the source or origin of something

occurrences of the phrase "from" in various contexts

No Comments

No Known Activations