INDEX

Explanations

instances of specific named entities such as locations, names, and titles

oai_token-act-pair · gpt-3.5-turbo

mentions of specific locations and frequently asked questions (FAQs)

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

alez

-0.80

ration

-0.76

manship

-0.75

pend

-0.75

olic

-0.70

-0.66

RH

-0.65

 eleph

-0.64

itone

-0.64

cling

-0.63

POSITIVE LOGITS

sie

0.88

sheet

0.80

halla

0.77

 Takeru

0.75

bye

0.70

atoon

0.69

idges

0.68

ania

0.63

alkyrie

0.63

Activations Density 0.073%

instances of specific named entities such as locations, names, and titles

mentions of specific locations and frequently asked questions (FAQs)

No Comments

No Known Activations