INDEX

Explanations

dates or events mentioned within a specific range of a few days

oai_token-act-pair · gpt-3.5-turbo

dates and numerical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

minecraft

-0.71

cules

-0.70

dL

-0.67

ongyang

-0.65

 blaster

-0.65

hetically

-0.64

imar

-0.62

wered

-0.62

utra

-0.62

atsu

-0.61

POSITIVE LOGITS

pter

0.76

rules

0.73

ioxide

0.72

nect

0.64

 Process

0.64

ascript

0.64

 partName

0.62

arlane

0.61

Delivery

0.61

 Grounds

0.61

Activations Density 0.113%

dates or events mentioned within a specific range of a few days

dates and numerical references

No Comments

No Known Activations