INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

words related to individual or group identities and social handles

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

 optics

-0.67

-0.65

mosp

-0.64

net

-0.62

deck

-0.62

 shoulders

-0.62

 Attribution

-0.61

ENTION

-0.60

 accommodations

-0.60

 Immunity

-0.59

POSITIVE LOGITS

ppa

1.44

zzi

1.37

ppo

1.35

zzle

1.34

zza

1.32

pta

1.28

ppe

1.26

ÅŁ

1.24

jo

1.20

lda

1.19

Activations Density 0.230%

names of individuals

words related to individual or group identities and social handles

No Comments

No Known Activations