INDEX

Explanations

time-related information expressed in sentences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Around" followed by numerical values indicating quantity or time

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

xual

-0.75

qua

-0.71

ysis

-0.68

 Guilty

-0.62

 gard

-0.62

inen

-0.60

 Tigers

-0.59

ple

-0.57

elman

-0.57

aciously

-0.56

POSITIVE LOGITS

abouts

0.88

 corners

0.84

clock

0.75

«

0.70

 midday

0.70

scan

0.69

=~=~

0.69

 ..........

0.68

about

0.68

Activations Density 0.046%

time-related information expressed in sentences

occurrences of the word "Around" followed by numerical values indicating quantity or time

No Comments

No Known Activations