INDEX

Explanations

words related to elevating or raising something

oai_token-act-pair · gpt-3.5-turbo

terms related to elevators and elevation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãģ¦

-0.83

neg

-0.79

book

-0.75

ned

-0.75

cheat

-0.73

NEY

-0.72

nia

-0.72

ello

-0.72

ãĥ£

-0.71

ters

-0.71

POSITIVE LOGITS

 ceilings

0.91

 shaft

0.89

 heights

0.88

 elev

0.85

psey

0.77

 elevation

0.75

 altitude

0.74

ipl

0.74

 Everest

0.73

 lows

0.72

Activations Density 0.100%

words related to elevating or raising something

terms related to elevators and elevation

No Comments

No Known Activations