INDEX

Explanations

mentions of specific names or titles

oai_token-act-pair · gpt-3.5-turbo

instances of intent or knowledge related to actions and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LGBT

-0.84

Yeah

-0.80

 Fuck

-0.79

 Yeah

-0.79

Pretty

-0.78

gay

-0.77

yeah

-0.76

 yeah

-0.76

Fuck

-0.74

 Pretty

-0.74

POSITIVE LOGITS

 sufficient

1.02

 cumbers

0.96

 sufficiently

0.94

 ascertain

0.94

 satisf

0.93

 spontaneously

0.92

 diligent

0.92

 ascert

0.91

 contempor

0.90

 inadvert

0.90

Activations Density 1.581%

mentions of specific names or titles

instances of intent or knowledge related to actions and accountability

No Comments

No Known Activations