INDEX

Explanations

mentions of the word "Paris" in various contexts

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Masquerade

-0.66

 antid

-0.65

aph

-0.64

 assigning

-0.63

 deduct

-0.62

 destination

-0.61

 express

-0.60

terday

-0.60

Avg

-0.60

 alleg

-0.58

POSITIVE LOGITS

ris

4.62

rist

1.64

rison

1.56

rises

1.55

rys

1.43

rir

1.42

rus

1.39

ri

1.37

rett

1.34

rish

1.34

Activations Density 0.009%

mentions of the word "Paris" in various contexts

words related to the concept of risk

No Comments

No Known Activations