INDEX

Explanations

phrases related to demographics or geographic data

oai_token-act-pair · gpt-3.5-turbo

terms related to geography and demographic studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.79

fires

-0.74

nit

-0.74

practice

-0.72

street

-0.71

Mub

-0.70

itivity

-0.68

sticks

-0.68

icum

-0.67

INGTON

-0.67

POSITIVE LOGITS

ographic

1.06

ographically

0.95

ographics

0.91

oppable

0.83

ographical

0.81

ography

0.71

ographer

0.70

 demographics

0.69

ocument

0.69

 projection

0.68

Activations Density 0.014%

phrases related to demographics or geographic data

terms related to geography and demographic studies

No Comments

No Known Activations