INDEX

Explanations

proper nouns related to people or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific terms related to individuals or entities

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

ally

-0.88

oxin

-0.80

ORE

-0.77

ores

-0.75

ingly

-0.72

weed

-0.71

alid

-0.71

ande

-0.70

asted

-0.70

atoes

-0.70

POSITIVE LOGITS

soDeliveryDate

0.82

chant

0.82

cipl

0.73

thood

0.72

ãĥĥ

0.70

cipled

0.70

ħĭ

0.69

0.67

forming

0.67

âĸ¬âĸ¬

0.66

Activations Density 0.056%

proper nouns related to people or locations

proper nouns and specific terms related to individuals or entities

No Comments

No Known Activations