INDEX

Explanations

differences or exceptions in similar items

oai_token-act-pair · gpt-3.5-turbo

contrasting phrases or qualifiers in comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

onomy

-0.69

 FANTASY

-0.66

oe

-0.63

afa

-0.62

mma

-0.62

FU

-0.61

Occup

-0.60

abeth

-0.59

ute

-0.59

nation

-0.59

POSITIVE LOGITS

different

0.93

 differently

0.92

 differs

0.88

 sharper

0.88

 different

0.86

 differing

0.82

 Different

0.81

 wiser

0.80

 altered

0.80

 shorter

0.80

Activations Density 0.261%

differences or exceptions in similar items

contrasting phrases or qualifiers in comparisons

No Comments

No Known Activations