INDEX

Explanations

terms related to deterring actions or consequences

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>

-2.02

DataPropertyName

-0.70

/***

-0.63

<?

-0.61

 дописавши

-0.61

PrintStream

-0.61

/*!

-0.60

 superintend

-0.60

mAdapter

-0.59

 Román

-0.59

POSITIVE LOGITS

 deterrent

0.92

 deterred

0.86

 tucson

0.84

 riva

0.82

 borsa

0.80

arture

0.80

 deterrence

0.80

relenting

0.80

tph

0.80

leuth

0.79

Activations Density 0.146%

terms related to deterring actions or consequences

No Comments

No Known Activations