INDEX

Explanations

terms related to diminishing or reducing something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "down" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.72

andum

-0.67

ista

-0.67

archives

-0.60

 Markus

-0.60

OPLE

-0.58

olkien

-0.58

ificent

-0.58

Ã«

-0.57

tein

-0.57

POSITIVE LOGITS

graded

1.40

LOAD

1.30

grading

1.27

stairs

1.22

grades

1.16

hill

1.05

pour

1.03

loaded

1.01

sized

0.97

grade

0.93

Activations Density 0.043%

terms related to diminishing or reducing something

instances of the word "down" in various contexts

No Comments

No Known Activations