INDEX

Explanations

terms related to evasion or avoidance

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.28

<?

-0.67

Autoritní

-0.59

García

-0.54

 посла

-0.54

Література

-0.54

ánchez

-0.53

 لينك

-0.52

 servem

-0.52

 ويكي

-0.52

POSITIVE LOGITS

Ev

1.37

ev

1.21

Ev

1.20

EV

1.15

ev

1.09

 Evang

1.04

EV

0.98

 circon

0.96

 jaya

0.95

 catég

0.95

Activations Density 0.073%

terms related to evasion or avoidance

No Comments

No Known Activations