INDEX

Explanations

time durations related to personal experiences or events

oai_token-act-pair · gpt-3.5-turbo

references to durations of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

gall

-0.68

egu

-0.66

values

-0.64

raviolet

-0.61

Redd

-0.61

cheat

-0.61

alg

-0.60

Ry

-0.60

ocl

-0.59

rote

-0.59

POSITIVE LOGITS

 apiece

0.99

 consecut

0.99

ago

0.92

 uninterrupted

0.90

 thereafter

0.88

 straight

0.87

 consecutive

0.87

 afterward

0.85

ruary

0.83

until

0.82

Activations Density 0.104%

time durations related to personal experiences or events

references to durations of time

No Comments

No Known Activations