INDEX

Explanations

locations or directions within an environment

oai_token-act-pair · gpt-3.5-turbo

locations or places within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ohyd

-0.69

Ô

-0.69

anson

-0.68

thood

-0.67

NECT

-0.66

NetMessage

-0.65

ccording

-0.65

rosso

-0.62

 homegrown

-0.61

 Month

-0.61

POSITIVE LOGITS

 doorway

0.82

 ceiling

0.80

 floor

0.79

 courtyard

0.79

 hallway

0.78

 aisle

0.77

 fireplace

0.77

 confines

0.76

 vicinity

0.76

osphere

0.75

Activations Density 0.316%

locations or directions within an environment

locations or places within a narrative

No Comments

No Known Activations