INDEX

Explanations

German words or phrases

oai_token-act-pair · gpt-3.5-turbo

words related to negative or undesirable qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

culus

-0.89

ebus

-0.82

culated

-0.80

anmar

-0.75

NCT

-0.72

apego

-0.72

ationally

-0.71

ãĤ£

-0.71

 restrooms

-0.69

 ILCS

-0.69

POSITIVE LOGITS

entimes

0.91

iller

0.77

enger

0.75

\\\\\\\\\\\\\\\\

0.73

ying

0.73

linger

0.72

mann

0.72

iness

0.71

nown

0.70

erent

0.69

Activations Density 0.011%

German words or phrases

words related to negative or undesirable qualities

No Comments

No Known Activations