INDEX

Explanations

words related to the location "Concord."

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographic locations or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

male

-0.88

icz

-0.83

geons

-0.82

ener

-0.81

pping

-0.79

dy

-0.77

elling

-0.77

geon

-0.76

lass

-0.76

aughter

-0.75

POSITIVE LOGITS

 Triangle

0.93

 Papers

0.92

 Ridge

0.89

 Carbuncle

0.88

 Sage

0.86

 Corridor

0.80

 Scholar

0.80

 Trails

0.77

 Pathfinder

0.77

 Harmony

0.75

Activations Density 0.062%

words related to the location "Concord."

mentions of specific geographic locations or organizations

No Comments

No Known Activations