INDEX

Explanations

words related to human sexuality

oai_token-act-pair · gpt-3.5-turbo

topics related to sexuality and its various societal implications

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

Not in Any Lists

No Comments

Negative Logits

 Schne

-0.69

MER

-0.69

Pont

-0.68

CHA

-0.63

Ing

-0.62

Ing

-0.62

ãĥĥãĥĪ

-0.62

×©

-0.61

 Lama

-0.61

ACH

-0.60

POSITIVE LOGITS

uality

1.05

 Spectrum

0.78

creen

0.77

ophobia

0.74

 spectrum

0.73

oking

0.71

bian

0.71

isphere

0.71

odox

0.71

apore

0.71

Activations Density 0.027%

words related to human sexuality

topics related to sexuality and its various societal implications

No Comments

No Known Activations