INDEX

Explanations

words related to something that is urgently required or a long-anticipated event

oai_token-act-pair · gpt-3.5-turbo

terms indicating necessity or urgent need

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alos

-0.77

forums

-0.72

opers

-0.72

lua

-0.71

eligible

-0.71

uits

-0.70

arij

-0.70

builders

-0.70

paio

-0.70

flix

-0.69

POSITIVE LOGITS

 farewell

0.82

 optimism

0.79

 Parenthood

0.76

 prosperity

0.75

 birthday

0.72

 wisdom

0.71

 humanitarian

0.69

 irony

0.68

ãĤ´ãĥ³

0.68

 childhood

0.68

Activations Density 0.082%

words related to something that is urgently required or a long-anticipated event

terms indicating necessity or urgent need

No Comments

No Known Activations