INDEX

Explanations

phrases related to increasing probability or likelihood of an event happening

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate increases in probability or risk

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

omorphic

-0.80

oros

-0.76

REDACTED

-0.69

icians

-0.68

bern

-0.68

apers

-0.66

bos

-0.66

interstitial

-0.64

annot

-0.64

mega

-0.63

POSITIVE LOGITS

 exponentially

0.88

 dramatically

0.80

 footprint

0.80

 considerably

0.76

 dependency

0.75

 enormously

0.70

 morale

0.70

 drastically

0.70

 substantially

0.70

 visibility

0.69

Activations Density 0.462%

phrases related to increasing probability or likelihood of an event happening

phrases that indicate increases in probability or risk

No Comments

No Known Activations