INDEX

Explanations

the word "podium"

oai_token-act-pair · gpt-3.5-turbo

references to podiums and speaking engagements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Disease

-0.69

Operation

-0.68

 Sins

-0.65

Mut

-0.64

version

-0.62

 Flesh

-0.61

ay

-0.61

sin

-0.61

Allen

-0.60

Scan

-0.60

POSITIVE LOGITS

 podium

4.09

 microphone

1.38

 pedest

1.34

 lect

1.25

 throne

1.15

 scoreboard

1.12

 microphones

1.09

 lapt

1.07

 stage

1.06

 pole

1.06

Activations Density 0.015%

the word "podium"

references to podiums and speaking engagements

No Known Activations