INDEX

Explanations

descriptions of scientific studies and experiments

oai_token-act-pair · gpt-3.5-turbo

phrases related to research studies and experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ANC

-0.71

REF

-0.69

~~~~~~~~

-0.68

Capital

-0.66

dyl

-0.65

 symbol

-0.65

ãĥķãĤ©

-0.65

 regrets

-0.63

 trump

-0.62

 Gork

-0.62

POSITIVE LOGITS

 randomized

1.02

otype

0.99

 samples

0.99

 volunteers

0.92

 Participants

0.91

sample

0.91

 participants

0.91

 study

0.90

 sample

0.90

 Experiment

0.90

Activations Density 0.784%

descriptions of scientific studies and experiments

phrases related to research studies and experiments

No Comments

No Known Activations