INDEX

Explanations

phrases related to prohibitions or restrictions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating negation or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Reloaded

-0.81

 Reborn

-0.72

 "$:/

-0.70

 Royale

-0.69

 vind

-0.68

 restored

-0.68

 chapter

-0.66

 Fork

-0.66

gypt

-0.63

 Unch

-0.63

POSITIVE LOGITS

brainer

1.31

strings

1.16

repeat

1.13

exc

1.11

reply

1.09

smoking

1.08

contact

1.08

platform

1.05

matter

1.03

notice

1.02

Activations Density 0.016%

phrases related to prohibitions or restrictions

phrases indicating negation or absence

No Comments

No Known Activations