INDEX

Explanations

references to the prefix "neo-" in the text

oai_token-act-pair · gpt-3.5-turbo

references to neo-Nazi ideology and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

hips

-0.77

 thumbnail

-0.72

lessly

-0.64

 balloons

-0.63

 jars

-0.62

loo

-0.61

 reservoirs

-0.60

 baskets

-0.60

 Rings

-0.60

ositories

-0.59

POSITIVE LOGITS

Nazi

0.96

ge

0.90

0.89

ethical

0.89

christ

0.88

-)

0.88

engineering

0.88

femin

0.87

entimes

0.84

fascist

0.84

Activations Density 0.028%

references to the prefix "neo-" in the text

references to neo-Nazi ideology and related terms

No Comments

No Known Activations