INDEX

Explanations

expressions related to probability or likelihood

oai_token-act-pair · gpt-3.5-turbo

phrases related to probabilities and betting situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

"},

-0.75

ãĥ¬

-0.71

ertodd

-0.71

ãĥ¡

-0.69

ivation

-0.66

ONSORED

-0.65

avior

-0.64

kamp

-0.63

ptoms

-0.62

andise

-0.62

POSITIVE LOGITS

 slim

0.86

 darn

0.76

 damned

0.72

LOT

0.71

 stacked

0.68

 guessed

0.65

 whoever

0.65

 good

0.64

 high

0.64

footed

0.63

Activations Density 0.075%

expressions related to probability or likelihood

phrases related to probabilities and betting situations

No Comments

No Known Activations