INDEX

Explanations

references to specific geographical locations, specifically Greenland and Gujarat

oai_token-act-pair · gpt-3.5-turbo

references to geographic locations, specifically Greenland and Gujarat

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

hemat

-0.94

otle

-0.93

yll

-0.85

intosh

-0.84

Afee

-0.79

bery

-0.77

choes

-0.77

colo

-0.76

Ã£o

-0.74

yles

-0.74

POSITIVE LOGITS

 unification

0.84

ification

0.76

ified

0.73

 Fenrir

0.70

fires

0.66

 Scorpion

0.64

iosity

0.64

iant

0.64

 riots

0.64

ãĥ¼ãĥĨ

0.63

Activations Density 0.024%

references to specific geographical locations, specifically Greenland and Gujarat

references to geographic locations, specifically Greenland and Gujarat

No Comments

No Known Activations