INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

locations and specific geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 acron

-0.51

erity

-0.49

 positives

-0.49

 encyclopedia

-0.48

 latent

-0.47

 odds

-0.47

 secretaries

-0.46

 goose

-0.46

 prolonged

-0.46

 omission

-0.46

POSITIVE LOGITS

 Village

0.80

 Harbor

0.78

 Gardens

0.76

 Harbour

0.75

 Heights

0.75

 Island

0.74

 Township

0.74

hurst

0.74

town

0.74

 Meadows

0.73

Activations Density 0.570%

locations or places

locations and specific geographic references

No Comments

No Known Activations