INDEX

Explanations

phrases indicating examples or instances

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "being" and related forms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PsyNetMessage

-0.75

Dag

-0.71

 Beginning

-0.63

robat

-0.62

inav

-0.62

 sovere

-0.62

Lag

-0.60

odor

-0.59

 Album

-0.57

 Surv

-0.57

POSITIVE LOGITS

 able

1.10

 eaten

0.91

 discussed

0.89

 hailed

0.88

 replaced

0.88

 disposed

0.88

 consumed

0.88

held

0.87

 chased

0.87

 phased

0.86

Activations Density 0.057%

phrases indicating examples or instances

occurrences of the word "being" and related forms

No Comments

No Known Activations