INDEX

Explanations

positive adjectives describing products or characteristics

oai_token-act-pair · gpt-3.5-turbo

punctuations or lists that denote emphasis or separation in thoughts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStream

-0.99

ulla

-0.92

regation

-0.83

lication

-0.76

iatrics

-0.76

EMENT

-0.75

onica

-0.74

phia

-0.71

asio

-0.70

vation

-0.69

POSITIVE LOGITS

 albeit

1.00

 resilient

0.94

 witty

0.91

but

0.91

 efficient

0.91

 elegant

0.90

 insightful

0.89

 inefficient

0.88

 informative

0.87

 agile

0.86

Activations Density 0.207%

positive adjectives describing products or characteristics

punctuations or lists that denote emphasis or separation in thoughts

No Comments

No Known Activations