INDEX

Explanations

words related to different types of noises

oai_token-act-pair · gpt-3.5-turbo

terms related to noise levels and their effects

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

opez

-0.80

onz

-0.75

armac

-0.73

innon

-0.72

een

-0.71

folios

-0.71

zona

-0.71

vez

-0.70

erest

-0.70

alions

-0.69

POSITIVE LOGITS

 noise

0.95

 emitting

0.85

 Noise

0.85

 noises

0.83

 pollution

0.80

 emitted

0.79

 louder

0.78

 amplification

0.77

immune

0.74

 detectors

0.74

Activations Density 0.022%

words related to different types of noises

terms related to noise levels and their effects

No Comments

No Known Activations