INDEX

Explanations

celebrity names

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names

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

 multit

-0.78

 weap

-0.78

 multip

-0.76

 prest

-0.73

 puzz

-0.72

iP

-0.72

 toget

-0.71

 INTER

-0.70

SOC

-0.69

 seiz

-0.69

POSITIVE LOGITS

asaki

1.10

essa

1.08

elia

1.05

eria

1.05

ana

1.04

ida

1.03

atha

1.01

ola

1.01

onica

1.00

arie

1.00

Activations Density 0.289%

celebrity names

proper nouns and names

No Comments

No Known Activations