INDEX

Explanations

terms related to taking advantage of situations or individuals for personal gain

oai_token-act-pair · gpt-3.5-turbo

instances of the word "exploit" and its variations, indicating a focus on exploitation themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

thood

-0.84

 mint

-0.78

cas

-0.72

arat

-0.71

cone

-0.66

audi

-0.65

prints

-0.63

shake

-0.62

mad

-0.61

ucket

-0.61

POSITIVE LOGITS

 loopholes

1.04

 weaknesses

0.98

 exploited

0.97

 exploit

0.87

oit

0.85

 vulnerabilities

0.84

 exploiting

0.82

ulner

0.82

urous

0.80

 exploitation

0.79

Activations Density 0.031%

terms related to taking advantage of situations or individuals for personal gain

instances of the word "exploit" and its variations, indicating a focus on exploitation themes

No Comments

No Known Activations