INDEX

Explanations

descriptions or mentions of scientific experiments

oai_token-act-pair · gpt-3.5-turbo

references to scientific experiments

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

headers

-0.67

cut

-0.62

veland

-0.62

clinton

-0.60

doms

-0.60

lake

-0.59

othy

-0.59

ritic

-0.59

flush

-0.59

miah

-0.58

POSITIVE LOGITS

imental

1.06

iments

1.05

iment

0.91

ally

0.88

 Experiment

0.87

 experiment

0.81

eers

0.80

ually

0.75

uates

0.75

onom

0.73

Activations Density 0.016%

descriptions or mentions of scientific experiments

references to scientific experiments

No Comments

No Known Activations