INDEX

Explanations

words related to the term "Cer"

oai_token-act-pair · gpt-3.5-turbo

references to specific names or terms, particularly those starting with "Cer" and related variations

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

urst

-0.84

orb

-0.75

ãĥĥãĥĪ

-0.71

ive

-0.71

bow

-0.70

capital

-0.66

selves

-0.65

ivity

-0.65

owered

-0.64

icut

-0.64

POSITIVE LOGITS

flies

0.78

umo

0.75

osi

0.75

cle

0.75

wolves

0.75

ulia

0.75

lio

0.75

keley

0.74

wolf

0.74

nea

0.74

Activations Density 0.058%

words related to the term "Cer"

references to specific names or terms, particularly those starting with "Cer" and related variations

No Comments

No Known Activations