INDEX

Explanations

mentions of relationships involving teenage individuals

oai_token-act-pair · gpt-3.5-turbo

references to teenage individuals

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

ktop

-0.96

adr

-0.89

itsch

-0.89

ichick

-0.89

lda

-0.89

igslist

-0.87

ĪĴ

-0.86

daq

-0.85

xon

-0.83

odcast

-0.83

POSITIVE LOGITS

 boys

0.97

 girls

0.92

 adolesc

0.88

aged

0.83

 adulthood

0.81

 males

0.79

olesc

0.79

 angst

0.78

boy

0.78

 adolescence

0.77

Activations Density 0.016%

mentions of relationships involving teenage individuals

references to teenage individuals

No Comments

No Known Activations