INDEX

Explanations

statements related to legal actions or consequences

oai_token-act-pair · gpt-3.5-turbo

sentences that convey significant events or statements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ogyn

-0.78

hens

-0.73

mere

-0.68

Quote

-0.67

 disg

-0.65

oun

-0.65

 discontin

-0.65

berra

-0.64

anian

-0.63

 tremend

-0.63

POSITIVE LOGITS

 Replay

0.81

src

0.77

 Boko

0.69

 POLITICO

0.68

imeo

0.66

 Capitol

0.66

 Conversation

0.65

bernatorial

0.64

Ruk

0.63

inventoryQuantity

0.63

Activations Density 0.147%

statements related to legal actions or consequences

sentences that convey significant events or statements

No Known Activations