INDEX

Explanations

years or numerical values related to specific events or entities

oai_token-act-pair · gpt-3.5-turbo

numerical values related to years or statistical data

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

raltar

-0.83

ledged

-0.81

otle

-0.80

orius

-0.79

sonian

-0.77

awed

-0.76

urger

-0.76

intosh

-0.75

amaru

-0.73

fall

-0.73

POSITIVE LOGITS

nd

1.77

ND

0.93

0.82

 thirds

0.81

naire

0.80

0.78

ipop

0.77

entary

0.75

ength

0.75

mph

0.74

Activations Density 0.098%

years or numerical values related to specific events or entities

numerical values related to years or statistical data

No Comments

No Known Activations