INDEX

Explanations

locations, especially in relation to distance from a reference point

oai_token-act-pair · gpt-3.5-turbo

geographical distance references

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

onential

-0.74

>>>>>>>>

-0.73

 Flavoring

-0.72

aceous

-0.67

 Beans

-0.65

Wiki

-0.64

atonin

-0.62

 inval

-0.62

oly

-0.62

 refin

-0.62

POSITIVE LOGITS

 nearest

0.77

 Columbus

0.71

 Louisville

0.71

shore

0.70

lier

0.69

 latitude

0.69

 closest

0.69

 Amsterdam

0.67

 shore

0.67

atown

0.66

Activations Density 0.096%

locations, especially in relation to distance from a reference point

geographical distance references

No Comments

No Known Activations