INDEX

Explanations

phrases related to accounting or quantifying something

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "accounted" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

field

-0.68

enta

-0.66

 parting

-0.64

 Zion

-0.63

Hof

-0.61

 pity

-0.60

 Corona

-0.58

 Wichita

-0.57

raid

-0.56

 Patriarch

-0.56

POSITIVE LOGITS

ancy

0.93

enance

0.89

ality

0.87

ãĤ¼ãĤ¦ãĤ¹

0.86

ominated

0.82

 accounted

0.80

iciary

0.77

MpServer

0.76

iless

0.76

rations

0.75

Activations Density 0.004%

phrases related to accounting or quantifying something

mentions of the word "accounted" in various contexts

No Comments

No Known Activations