INDEX

Explanations

locations and spatial relationships between them

oai_token-act-pair · gpt-3.5-turbo

phrases indicating proximity or location, particularly related to streets and directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ivities

-0.76

ebus

-0.75

aki

-0.73

orian

-0.69

rogram

-0.68

ronic

-0.67

imony

-0.67

seed

-0.67

uffle

-0.66

omic

-0.65

POSITIVE LOGITS

 entrances

0.82

 downtown

0.79

 corner

0.77

 adjacent

0.77

 entrance

0.77

tyard

0.76

 overlook

0.76

 vicinity

0.75

rium

0.75

 campus

0.75

Activations Density 0.221%

locations and spatial relationships between them

phrases indicating proximity or location, particularly related to streets and directions

No Comments

No Known Activations