INDEX

Explanations

words related to transportation systems or infrastructure

oai_token-act-pair · gpt-3.5-turbo

references to "light" and "heavy" as descriptors, particularly in the context of weight or physical attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

=-=-

-0.72

å£«

-0.70

 Pact

-0.68

rency

-0.65

bid

-0.62

 Submission

-0.62

 Cosponsors

-0.60

aroo

-0.60

issance

-0.60

Assembly

-0.59

POSITIVE LOGITS

 candles

0.79

 shine

0.76

 lamps

0.75

dark

0.74

elight

0.72

raviolet

0.71

 lantern

0.71

 flickering

0.70

 shone

0.69

oresc

0.68

Activations Density 0.220%

words related to transportation systems or infrastructure

references to "light" and "heavy" as descriptors, particularly in the context of weight or physical attributes

No Comments

No Known Activations