INDEX

Explanations

words related to blurring, blending, or mixing information or visual elements

oai_token-act-pair · gpt-3.5-turbo

terms associated with obscurity or indistinctness

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

ept

-0.87

iott

-0.81

itutional

-0.74

CVE

-0.74

areth

-0.68

istrates

-0.68

EEK

-0.68

 Democr

-0.64

payers

-0.64

nai

-0.64

POSITIVE LOGITS

 blur

0.99

 blurred

0.98

rier

0.85

ected

0.79

alysed

0.78

urring

0.77

iform

0.77

 vision

0.74

 blurry

0.73

 deline

0.72

Activations Density 0.027%

words related to blurring, blending, or mixing information or visual elements

terms associated with obscurity or indistinctness

No Comments

No Known Activations