INDEX

Explanations

years mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

specific years

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

onite

-0.69

ãĤ´ãĥ³

-0.63

burning

-0.61

 chore

-0.60

artifacts

-0.57

venge

-0.56

 burner

-0.56

abilia

-0.56

EStreamFrame

-0.55

 conve

-0.55

POSITIVE LOGITS

 meanwhile

0.84

ruary

0.75

lance

0.75

athi

0.71

ileaks

0.70

 however

0.66

peak

0.66

ANN

0.64

rero

0.63

 Raphael

0.62

Activations Density 0.158%

years mentioned in the text

specific years

No Comments

No Known Activations