INDEX

Explanations

locations or areas within a setting

oai_token-act-pair · gpt-3.5-turbo

locations or places within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icter

-0.69

oice

-0.67

anish

-0.64

uggest

-0.64

 brittle

-0.63

versely

-0.61

arily

-0.58

pes

-0.57

arling

-0.56

iency

-0.55

POSITIVE LOGITS

tyard

1.08

 courtyard

0.92

 corridor

0.91

 corridors

0.89

 overlooking

0.88

 premises

0.85

 Corridor

0.84

 hallway

0.83

 restroom

0.83

 confines

0.82

Activations Density 0.750%

locations or areas within a setting

locations or places within a narrative context

No Comments

No Known Activations