INDEX

Explanations

locations or geographical references

oai_token-act-pair · gpt-3.5-turbo

geographic and location-based information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Opinion

-0.69

 Machina

-0.69

 Spoiler

-0.69

 mistakes

-0.68

matically

-0.68

 excuses

-0.68

reprene

-0.67

 incent

-0.66

 Rosenstein

-0.66

 Ranking

-0.65

POSITIVE LOGITS

 adjoining

1.04

 nearby

1.01

 southwestern

0.98

 lakes

0.96

 vicinity

0.95

 northeast

0.95

 adjacent

0.95

tnc

0.93

 southeastern

0.93

 airst

0.92

Activations Density 2.381%

locations or geographical references

geographic and location-based information

No Comments

No Known Activations