INDEX

Explanations

locations by identifying cardinal directions like north, south, east, and west

oai_token-act-pair · gpt-3.5-turbo

phrases indicating geographical relationships or locations

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

 Cosponsors

-0.91

 showc

-0.75

}}}

-0.69

Own

-0.68

iatric

-0.68

 submar

-0.66

 ratios

-0.65

itiveness

-0.65

Reviewer

-0.64

only

-0.63

POSITIVE LOGITS

 Appalach

0.85

 Lima

0.81

course

0.79

 course

0.76

 Route

0.75

 Interstate

0.74

outheast

0.71

 ours

0.71

 latitude

0.70

 bounds

0.70

Activations Density 0.061%

locations by identifying cardinal directions like north, south, east, and west

phrases indicating geographical relationships or locations

No Comments

No Known Activations