INDEX

Explanations

references to or mentions of neighbors

oai_token-act-pair · gpt-3.5-turbo

references to neighbors or neighboring relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uggage

-0.82

othal

-0.77

indal

-0.76

enei

-0.76

obin

-0.75

inen

-0.75

anwhile

-0.73

itech

-0.70

aneers

-0.69

xit

-0.68

POSITIVE LOGITS

 neighbor

1.09

 Neigh

1.07

 neighbors

0.98

 neighbour

0.94

liness

0.92

bors

0.91

folk

0.87

 neighbours

0.86

 Neighbor

0.84

hood

0.81

Activations Density 0.034%

references to or mentions of neighbors

references to neighbors or neighboring relationships

No Comments

No Known Activations