INDEX

Explanations

phrases including the word "definition."

oai_token-act-pair · gpt-3.5-turbo

the term "definition," particularly in various contexts and discussions about definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pload

-0.77

orld

-0.77

 Pradesh

-0.71

estern

-0.70

olulu

-0.70

rop

-0.66

ienced

-0.66

ocamp

-0.66

 Agric

-0.65

eor

-0.64

POSITIVE LOGITS

inition

0.98

 definitions

0.94

initions

0.92

 definition

0.91

 defines

0.84

witz

0.81

 Definition

0.75

definition

0.75

 criteria

0.75

VID

0.74

Activations Density 0.014%

phrases including the word "definition."

the term "definition," particularly in various contexts and discussions about definitions

No Comments

No Known Activations