INDEX

Explanations

words related to printing or printing-related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "elt" associated with various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

CVE

-0.81

 Occupations

-0.78

sets

-0.71

 reconc

-0.69

ãĤĭ

-0.68

nect

-0.68

portion

-0.65

spective

-0.64

isSpecialOrderable

-0.62

 gestation

-0.61

POSITIVE LOGITS

down

1.04

imes

0.94

orf

0.94

itudinal

0.89

usk

0.88

robe

0.88

downs

0.86

astic

0.82

owered

0.82

ronics

0.81

Activations Density 0.034%

words related to printing or printing-related terms

occurrences of the word "elt" associated with various contexts

No Comments

No Known Activations