INDEX

Explanations

references to Google or Google-related topics

oai_token-act-pair · gpt-3.5-turbo

mentions of Google and its products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mble

-0.88

alid

-0.79

iotic

-0.74

quez

-0.74

rone

-0.74

ivari

-0.70

swing

-0.70

racuse

-0.69

odic

-0.68

iosyncr

-0.68

POSITIVE LOGITS

plex

0.89

 Maps

0.82

 Doodle

0.81

 Glass

0.81

 Scholar

0.80

 Fiber

0.80

geist

0.79

 Ventures

0.75

 Chrome

0.74

Maps

0.74

Activations Density 0.014%

references to Google or Google-related topics

mentions of Google and its products or services

No Comments

No Known Activations