INDEX

Explanations

terms related to a step or method within a process

oai_token-act-pair · gpt-3.5-turbo

references to various processes

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

azines

-0.73

azo

-0.70

 Fighters

-0.64

arus

-0.64

hiro

-0.63

 Haram

-0.61

selves

-0.61

isd

-0.61

 Falcons

-0.61

glers

-0.60

POSITIVE LOGITS

ional

1.23

ions

1.05

ioned

0.93

ivity

0.89

 whereby

0.89

ivism

0.83

ion

0.78

icity

0.77

ually

0.75

ors

0.75

Activations Density 0.047%

terms related to a step or method within a process

references to various processes

No Comments

No Known Activations