INDEX

Explanations

phrases indicating choice or alternative options

oai_token-act-pair · gpt-3.5-turbo

conditional phrases indicating alternative scenarios or possibilities

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

-0.74

ETS

-0.69

ocracy

-0.66

©¶æ

-0.65

Pen

-0.65

kamp

-0.65

\":

-0.65

)|

-0.64

onomy

-0.64

\/

-0.64

POSITIVE LOGITS

 alternatively

1.31

 simply

1.13

 outright

1.07

 else

1.05

 merely

0.95

chard

0.91

 maybe

0.89

 downright

0.86

phans

0.86

 worse

0.84

Activations Density 0.141%

phrases indicating choice or alternative options

conditional phrases indicating alternative scenarios or possibilities

No Comments

No Known Activations