INDEX

Explanations

words related to official documents, protocol, and authorities

oai_token-act-pair · gpt-3.5-turbo

references to the term "D" in various contexts, often related to diagnoses or classifications

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

éĹĺ

-0.81

ãĤ¡

-0.76

Io

-0.66

cov

-0.66

zai

-0.65

 Remem

-0.64

ItemTracker

-0.63

 Bulg

-0.62

Nun

-0.62

ppo

-0.62

POSITIVE LOGITS

etermin

1.08

etermination

1.06

ividual

1.06

ynam

1.03

iscovery

1.03

imensional

1.02

etermined

0.98

ictionary

0.97

REAM

0.97

ollar

0.97

Activations Density 0.033%

words related to official documents, protocol, and authorities

references to the term "D" in various contexts, often related to diagnoses or classifications

No Comments

No Known Activations