INDEX

Explanations

words related to mistakes or errors

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "mis" indicating incorrectness or errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hetti

-0.76

Â¯Â¯Â¯Â¯

-0.70

jriwal

-0.68

INGS

-0.65

 Enhancement

-0.64

ieri

-0.63

 Parties

-0.62

 Dynamics

-0.62

è¯

-0.62

 unto

-0.61

POSITIVE LOGITS

cellaneous

1.30

appropri

1.26

pell

1.12

pelled

1.09

beh

1.07

informed

1.02

behavior

1.01

pelling

0.97

aligned

0.97

jud

0.96

Activations Density 0.018%

words related to mistakes or errors

instances of the prefix "mis" indicating incorrectness or errors

No Comments

No Known Activations