INDEX

Explanations

keywords related to security breaches or unauthorized access

oai_token-act-pair · gpt-3.5-turbo

terms related to intrusions and breaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

å§«

-0.96

ndra

-0.96

baum

-0.90

wagen

-0.90

creen

-0.86

IELD

-0.81

hare

-0.75

nah

-0.74

BALL

-0.74

FUL

-0.72

POSITIVE LOGITS

 intr

1.20

uders

1.00

uding

0.91

inx

0.89

usions

0.84

ishly

0.81

 intruder

0.79

agg

0.79

igent

0.78

aband

0.76

Activations Density 0.006%

keywords related to security breaches or unauthorized access

terms related to intrusions and breaches

No Comments

No Known Activations