INDEX

Explanations

geographical locations specifically related to mountains

oai_token-act-pair · gpt-3.5-turbo

frequent mentions of "Mountain" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ional

-1.00

lest

-0.83

metic

-0.80

isen

-0.79

orate

-0.77

ivity

-0.77

soc

-0.76

alien

-0.76

earance

-0.76

emis

-0.75

POSITIVE LOGITS

 Mountain

1.23

 Riders

0.94

 Island

0.89

 Valley

0.88

ountain

0.88

 Mountains

0.85

 Bike

0.84

 Alto

0.83

 biking

0.82

 Meadows

0.82

Activations Density 0.009%

geographical locations specifically related to mountains

frequent mentions of "Mountain" in various contexts

No Comments

No Known Activations