INDEX

Explanations

instances where something is physically or figuratively close in proximity

oai_token-act-pair · gpt-3.5-turbo

phrases or contexts indicating proximity or becoming nearer to something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anity

-0.78

Ox

-0.77

EVA

-0.73

NZ

-0.72

hal

-0.71

DN

-0.71

SS

-0.69

plain

-0.68

DOM

-0.68

tech

-0.68

POSITIVE LOGITS

 closer

1.08

 "$:/

0.92

 examination

0.90

 scrutiny

0.89

 referen

0.84

 confid

0.82

 proximity

0.82

 clos

0.81

 nearer

0.81

 dilig

0.80

Activations Density 0.007%

instances where something is physically or figuratively close in proximity

phrases or contexts indicating proximity or becoming nearer to something

No Comments

No Known Activations