INDEX

Explanations

specific adjectives describing certain characteristics or states, often related to evaluations or assessments

oai_token-act-pair · gpt-3.5-turbo

terms that describe intensity and significance 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

abases

-0.96

assies

-0.96

lees

-0.92

mails

-0.90

alks

-0.88

tags

-0.87

ernels

-0.85

ramids

-0.83

bots

-0.83

classes

-0.81

POSITIVE LOGITS

 fixture

1.24

 occurrence

1.21

 manifestation

1.14

 reminder

1.11

 staple

1.11

 contender

1.10

 nuisance

1.09

 affair

1.08

 phenomenon

1.08

 testament

1.07

Activations Density 0.369%

specific adjectives describing certain characteristics or states, often related to evaluations or assessments

terms that describe intensity and significance in various contexts

No Comments

No Known Activations