INDEX

Explanations

dates and locations, specifically focusing on "on" and "at" phrases

oai_token-act-pair · gpt-3.5-turbo

occurrences of the words "on" and "at" indicating dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

TextColor

-0.76

ERC

-0.75

selves

-0.71

FontSize

-0.69

ERA

-0.66

 impunity

-0.66

Ĥª

-0.66

AG

-0.63

izoph

-0.62

YC

-0.62

POSITIVE LOGITS

 Â·

0.62

 Dustin

0.62

Tue

0.61

Posted

0.60

 Squirrel

0.60

Fri

0.60

 Blog

0.59

 arri

0.59

 Scrib

0.59

Apr

0.59

Activations Density 0.068%

dates and locations, specifically focusing on "on" and "at" phrases

occurrences of the words "on" and "at" indicating dates and times

No Comments

No Known Activations