INDEX

Explanations

references to disregarding or ignoring certain information or instructions

oai_token-act-pair · gpt-3.5-turbo

terms related to disregard or negligence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

oshenko

-0.82

izont

-0.82

ãĤ£

-0.80

izons

-0.77

 mosqu

-0.75

iatus

-0.72

Afee

-0.70

ites

-0.68

Kov

-0.66

Ó

-0.65

POSITIVE LOGITS

entimes

0.84

ortment

0.81

ulatory

0.72

 sund

0.70

ulations

0.69

rule

0.69

ful

0.68

arding

0.68

bard

0.68

LESS

0.67

Activations Density 0.027%

references to disregarding or ignoring certain information or instructions

terms related to disregard or negligence

No Comments

No Known Activations