INDEX

Explanations

terms related to colocalization in scientific contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "local."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 weeds

-0.76

 tumble

-0.74

 Jane

-0.72

bags

-0.72

Vik

-0.70

apr

-0.69

 rake

-0.67

MAT

-0.65

 curse

-0.65

Vi

-0.62

POSITIVE LOGITS

ocal

4.71

ocally

2.44

ocate

1.16

ibr

1.15

ohyd

1.15

ocation

1.13

oc

1.12

obar

1.08

anguage

1.06

ocus

1.06

Activations Density 0.019%

terms related to colocalization in scientific contexts

instances of the word "local."

No Comments

No Known Activations