INDEX

Explanations

events or situations occurring in the past

oai_token-act-pair · gpt-3.5-turbo

phrases indicating time, specifically those referring to duration or past events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pert

-0.79

ithing

-0.70

rongh

-0.69

ulkan

-0.67

acus

-0.65

ortment

-0.65

cellence

-0.63

 nont

-0.63

minecraft

-0.62

nostic

-0.62

POSITIVE LOGITS

 enough

0.99

aneously

0.92

 Enough

0.82

enough

0.78

Enough

0.74

 Pradesh

0.72

 anymore

0.68

ago

0.67

shots

0.65

 leftists

0.64

Activations Density 0.040%

events or situations occurring in the past

phrases indicating time, specifically those referring to duration or past events

No Comments

No Known Activations