INDEX

Explanations

the word "signal" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to various types of signals, particularly in scientific contexts

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

amily

-0.84

ucket

-0.76

ski

-0.75

ean

-0.74

sm

-0.74

endor

-0.73

cember

-0.71

erity

-0.71

eenth

-0.69

hur

-0.68

POSITIVE LOGITS

 signals

1.04

 handlers

0.92

 signal

0.90

 flares

0.81

 emanating

0.81

 handler

0.80

 transmissions

0.79

 signaling

0.76

 Signal

0.76

 signatures

0.75

Activations Density 0.033%

the word "signal" or variations of it

references to various types of signals, particularly in scientific contexts

No Comments

No Known Activations