INDEX

Explanations

phrases indicating likelihood or probability

oai_token-act-pair · gpt-3.5-turbo

phrases related to probabilities and chances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

rawdownloadcloneembedreportprint

-0.72

 Cheong

-0.69

jriwal

-0.67

ertodd

-0.65

ventus

-0.65

iband

-0.63

/**

-0.62

oru

-0.60

 Klux

-0.58

ivation

-0.58

POSITIVE LOGITS

 slim

0.74

Fay

0.73

 fingers

0.72

 damned

0.68

 guessed

0.68

none

0.66

 abound

0.66

LOT

0.64

footed

0.64

izoph

0.64

Activations Density 0.073%

phrases indicating likelihood or probability

phrases related to probabilities and chances

No Comments

No Known Activations