INDEX

Explanations

phrases related to controversial topics or actions

oai_token-act-pair · gpt-3.5-turbo

key phrases related to discoveries and significant events

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

!.

-0.77

KNOWN

-0.65

URA

-0.64

 scrut

-0.63

};

-0.63

+.

-0.62

ANI

-0.62

!,

-0.60

TPPStreamerBot

-0.57

';

-0.57

POSITIVE LOGITS

 lacks

0.74

 shouldn

0.72

isn

0.66

 violates

0.64

 outweigh

0.64

 should

0.63

 proves

0.63

 represents

0.63

 undermines

0.63

 constitutes

0.62

Activations Density 1.039%

phrases related to controversial topics or actions

key phrases related to discoveries and significant events

No Comments

No Known Activations