INDEX

Explanations

vocabulary related to various threats mentioned in a given context

oai_token-act-pair · gpt-3.5-turbo

references to various threats, particularly in a geopolitical context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ricks

-0.79

urses

-0.75

arist

-0.73

uesday

-0.70

alt

-0.68

Band

-0.68

uties

-0.68

ashion

-0.67

ools

-0.67

mys

-0.66

POSITIVE LOGITS

 posed

1.05

 threat

0.98

threat

0.89

 Threat

0.87

 threats

0.87

crow

0.81

 deterrent

0.81

 glare

0.79

xual

0.75

 detection

0.74

Activations Density 0.037%

vocabulary related to various threats mentioned in a given context

references to various threats, particularly in a geopolitical context

No Known Activations