INDEX

Explanations

different facts or statements being highlighted or emphasized

oai_token-act-pair · gpt-3.5-turbo

statements that present facts or assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

avorite

-0.76

TPPStreamerBot

-0.76

interstitial

-0.76

XY

-0.70

 throat

-0.69

 throats

-0.66

ESE

-0.65

 livest

-0.64

 pige

-0.62

DER

-0.61

POSITIVE LOGITS

ually

1.13

orial

1.00

uality

0.99

oids

0.92

itious

0.90

ional

0.89

oid

0.85

uated

0.83

icity

0.82

ual

0.82

Activations Density 0.017%

different facts or statements being highlighted or emphasized

statements that present facts or assertions

No Comments

No Known Activations