INDEX

Explanations

references to the brand "Honda"

oai_token-act-pair · gpt-3.5-turbo

references to the Honda brand and its models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ablishment

-0.95

vironment

-0.84

acular

-0.82

asure

-0.80

byter

-0.79

onyms

-0.77

ngth

-0.77

 Seym

-0.77

orial

-0.77

utherford

-0.76

POSITIVE LOGITS

 Civic

1.06

 Accord

0.89

 Honda

0.88

 Motor

0.87

 Odyssey

0.73

uana

0.72

Motor

0.71

 dealership

0.69

ota

0.69

Fit

0.68

Activations Density 0.011%

references to the brand "Honda"

references to the Honda brand and its models

No Comments

No Known Activations