INDEX

Explanations

instances where things are physically or metaphorically open

oai_token-act-pair · gpt-3.5-turbo

references to doors or openings, both literal and metaphorical

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

âĵĺ

-0.78

 endors

-0.61

 Voice

-0.60

ivan

-0.58

ahon

-0.58

Fan

-0.56

Ranked

-0.56

von

-0.56

member

-0.56

 metals

-0.55

POSITIVE LOGITS

ahead

0.80

ource

0.80

oresc

0.77

iltr

0.73

doors

0.73

 pores

0.73

 doors

0.72

 Doors

0.70

 indefinitely

0.69

 minded

0.69

Activations Density 0.064%

instances where things are physically or metaphorically open

references to doors or openings, both literal and metaphorical

No Known Activations