INDEX

Explanations

terms related to abuse

oai_token-act-pair · gpt-3.5-turbo

references to instances of abuse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cil

-0.79

travel

-0.74

izen

-0.71

pard

-0.71

views

-0.70

ript

-0.67

vision

-0.66

aries

-0.65

pai

-0.65

soType

-0.64

POSITIVE LOGITS

 perpetrated

0.97

 inflicted

0.95

abuse

0.95

 abuse

0.88

 abusing

0.84

 abused

0.80

 victims

0.79

 abusers

0.77

 survivors

0.77

 abuses

0.73

Activations Density 0.052%

terms related to abuse

references to instances of abuse

No Comments

No Known Activations