INDEX

Explanations

words or phrases prefixed with a specific symbol or word

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "f."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Das

-0.70

 paraly

-0.68

 Lizard

-0.67

 Came

-0.67

 Hammer

-0.66

 tone

-0.65

rawdownloadcloneembedreportprint

-0.63

 messenger

-0.63

 gent

-0.61

 machine

-0.61

POSITIVE LOGITS

ertility

1.34

ruits

1.20

actory

1.15

raction

1.15

andom

1.14

idelity

1.11

avorable

1.11

riction

1.09

ranch

1.09

rozen

1.07

Activations Density 0.019%

words or phrases prefixed with a specific symbol or word

occurrences of the letter "f."

No Comments

No Known Activations