INDEX

Explanations

instances where something is not excessively difficult or negative

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a mild degree of difficulty or moderation in quality

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

hyde

-0.88

ãĥ¼ãĥĨãĤ£

-0.78

otte

-0.75

iens

-0.69

oris

-0.69

intel

-0.69

arium

-0.66

intosh

-0.66

comings

-0.64

inators

-0.63

POSITIVE LOGITS

 much

0.82

 busy

0.79

ooo

0.72

 darn

0.72

 noticeable

0.71

len

0.70

 bright

0.70

 neat

0.70

 close

0.69

 flashy

0.68

Activations Density 0.026%

instances where something is not excessively difficult or negative

phrases indicating a mild degree of difficulty or moderation in quality

No Comments

No Known Activations