INDEX

Explanations

phrases related to manufacturing processes or specialized technical terms

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific set of entities or items identified by the term "elt."

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

 Occupations

-0.76

spective

-0.75

CVE

-0.73

sets

-0.71

perty

-0.69

credit

-0.68

nect

-0.64

 reconc

-0.64

 Bakr

-0.64

direction

-0.64

POSITIVE LOGITS

down

0.94

imes

0.92

mann

0.87

orf

0.85

acht

0.81

downs

0.80

itudinal

0.80

robe

0.78

itudes

0.76

kamp

0.75

Activations Density 0.018%

phrases related to manufacturing processes or specialized technical terms

mentions of a specific set of entities or items identified by the term "elt."

No Comments

No Known Activations