INDEX

Explanations

words related to velocity or speed

oai_token-act-pair · gpt-3.5-turbo

terms related to speed or velocity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ardless

-0.80

bery

-0.76

omes

-0.76

AME

-0.75

bor

-0.75

OME

-0.74

riad

-0.72

nie

-0.69

sbm

-0.69

ahime

-0.69

POSITIVE LOGITS

 velocity

1.22

ocity

1.11

Vel

0.90

 Velocity

0.83

 targ

0.78

 unbeliev

0.78

 mosqu

0.77

 sickness

0.77

 altitude

0.77

 sensations

0.76

Activations Density 0.011%

words related to velocity or speed

terms related to speed or velocity

No Comments

No Known Activations