INDEX

Explanations

terms related to mapping or converting processes, particularly involving data or physical spaces

oai_token-act-pair · gpt-3.5-turbo

concepts related to mapping and modeling processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ggy

-0.74

zone

-0.70

idity

-0.70

wife

-0.69

emate

-0.69

win

-0.69

cake

-0.69

bags

-0.67

fighter

-0.67

uous

-0.65

POSITIVE LOGITS

 electron

0.82

PsyNetMessage

0.79

hod

0.78

 mapping

0.76

ãĤ¼ãĤ¦ãĤ¹

0.73

ĸļ

0.71

 algorithms

0.71

ops

0.66

 seismic

0.66

 sensit

0.66

Activations Density 0.057%

terms related to mapping or converting processes, particularly involving data or physical spaces

concepts related to mapping and modeling processes

No Comments

No Known Activations