INDEX

Explanations

phrases describing specific entities or actions

oai_token-act-pair · gpt-3.5-turbo

references to specific people, organizations, or entities involved in various contexts

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

NetMessage

-0.80

interstitial

-0.72

©¶æ¥µ

-0.71

UGC

-0.70

Topic

-0.67

\">

-0.66

EStreamFrame

-0.64

ONT

-0.63

"]=>

-0.62

.............

-0.62

POSITIVE LOGITS

 fails

1.04

 succeeds

1.04

 decides

0.85

 chooses

0.84

 hadn

0.84

 survives

0.84

 somehow

0.84

 persists

0.84

 weren

0.84

 decide

0.82

Activations Density 0.315%

phrases describing specific entities or actions

references to specific people, organizations, or entities involved in various contexts

No Known Activations