INDEX

Explanations

references to missions or tasks

oai_token-act-pair · gpt-3.5-turbo

references to specific missions or tasks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģį

-0.76

Column

-0.74

picking

-0.74

 Ange

-0.69

batch

-0.65

amera

-0.65

weak

-0.65

urrency

-0.65

cling

-0.64

Prev

-0.64

POSITIVE LOGITS

arily

0.88

eers

0.86

 creep

0.84

 missions

0.84

 Impossible

0.82

 mission

0.80

 undertaken

0.77

 abroad

0.76

Vie

0.74

 accomplished

0.74

Activations Density 0.019%

references to missions or tasks

references to specific missions or tasks

No Comments

No Known Activations