INDEX

Explanations

mentions of the specific term "Grand" followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to "Grand," likely indicating locations or entities associated with that name

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

Downloadha

-0.93

PsyNetMessage

-0.81

lihood

-0.78

tics

-0.74

ylon

-0.72

utics

-0.70

ople

-0.70

phrine

-0.67

ijk

-0.66

anwhile

-0.66

POSITIVE LOGITS

father

1.22

 Prix

1.17

mother

1.13

parents

1.04

iosity

1.01

master

1.00

pa

0.97

 Theft

0.97

 Rapids

0.93

view

0.89

Activations Density 0.010%

mentions of the specific term "Grand" followed by a number

references to "Grand," likely indicating locations or entities associated with that name

No Comments

No Known Activations