INDEX

Explanations

terms related to difficulty and ease of tasks or experiences

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.00

 intersper

-1.34

fuf

-1.05

 encomp

-1.00

 unspeak

-0.96

 indestru

-0.94

 endeav

-0.93

 apprehen

-0.93

 endeavouring

-0.93

 disagre

-0.87

POSITIVE LOGITS

peated

0.70

gruntled

0.69

 Vergine

0.69

 croce

0.69

gusted

0.66

FORMANCE

0.63

atiable

0.63

astrous

0.62

fortable

0.58

levance

0.58

Activations Density 0.256%

terms related to difficulty and ease of tasks or experiences

No Comments

No Known Activations