INDEX

Explanations

mentions of the word "ford"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ford" and its variations

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

ntil

-0.76

 psychiat

-0.76

 exha

-0.76

pac

-0.74

 reinforcement

-0.74

 downside

-0.72

 insure

-0.71

 indo

-0.71

 sober

-0.70

 takeoff

-0.68

POSITIVE LOGITS

shire

1.49

ford

1.41

leigh

1.09

chester

1.07

hurst

1.05

wick

0.97

bridge

0.94

vill

0.94

combe

0.93

wall

0.92

Activations Density 0.012%

mentions of the word "ford"

occurrences of the word "ford" and its variations

No Comments

No Known Activations