INDEX

Explanations

specific locations and geographical references

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

expressions related to various geographical locations and traffic incidents

oai_token-act-pair · gpt-3.5-turbo

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

 submar

-0.83

 sailor

-0.77

 semen

-0.76

rogram

-0.76

iatric

-0.76

 saliva

-0.73

otle

-0.73

PLIED

-0.73

anguage

-0.71

 worms

-0.70

POSITIVE LOGITS

 Interstate

1.14

 Corridor

1.12

 Avenue

1.09

 Boulevard

1.08

 Plaza

1.06

 intersection

1.01

 Highway

1.00

 freeway

1.00

 roadway

1.00

 Blvd

0.98

Activations Density 0.661%

specific locations and geographical references

expressions related to various geographical locations and traffic incidents

No Comments

No Known Activations