INDEX

Explanations

words related to safety

oai_token-act-pair · gpt-3.5-turbo

mentions of safety 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

issance

-0.93

eric

-0.87

yss

-0.85

naire

-0.84

sonian

-0.81

ette

-0.80

eta

-0.76

dx

-0.75

nant

-0.74

fred

-0.73

POSITIVE LOGITS

 safety

0.88

ailability

0.80

 practition

0.80

 hazards

0.78

 margins

0.77

 valve

0.76

 isot

0.76

net

0.72

 precautions

0.71

ntil

0.71

Activations Density 0.028%

words related to safety

mentions of safety in various contexts

No Comments

No Known Activations