INDEX

Explanations

locations or places in proximity to a given point

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "nearby."

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

icer

-0.86

chin

-0.83

ppe

-0.82

inen

-0.78

apego

-0.78

xml

-0.76

xx

-0.75

istry

-0.74

ocker

-0.74

ioxide

-0.73

POSITIVE LOGITS

 nearby

1.06

 neighbors

0.99

 vicinity

0.95

 neighbor

0.94

 neighbours

0.90

 neighbour

0.88

 adjacent

0.81

 allied

0.80

 town

0.78

 neighboring

0.77

Activations Density 0.017%

locations or places in proximity to a given point

occurrences of the word "nearby."

No Comments

No Known Activations