INDEX

Explanations

timestamps related to events or news updates

oai_token-act-pair · gpt-3.5-turbo

instances of the word "earlier" followed by a time reference

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

 favour

-0.72

Baby

-0.71

SIM

-0.65

ismo

-0.65

adr

-0.64

aden

-0.62

qt

-0.62

package

-0.61

 scissors

-0.60

abl

-0.59

POSITIVE LOGITS

noon

0.97

 editions

0.85

 versions

0.80

theless

0.78

 recap

0.78

 Languages

0.75

nesses

0.74

 Releases

0.73

 Thoughts

0.70

 referen

0.68

Activations Density 0.056%

timestamps related to events or news updates

instances of the word "earlier" followed by a time reference

No Comments

No Known Activations