INDEX

Explanations

words related to actions of allocating resources or causing movements

oai_token-act-pair · gpt-3.5-turbo

words related to provocation and location

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mar

-0.71

test

-0.67

arat

-0.66

sonian

-0.65

character

-0.64

enez

-0.63

erer

-0.60

 dred

-0.59

 Answers

-0.59

mys

-0.58

POSITIVE LOGITS

entric

1.02

eus

0.89

atives

0.88

ATIVE

0.79

aukee

0.76

ocation

0.75

ptives

0.75

ISION

0.74

 Franch

0.72

lear

0.72

Activations Density 0.013%

words related to actions of allocating resources or causing movements

words related to provocation and location

No Comments

No Known Activations