INDEX

Explanations

references to advertisements and their presence in various contexts

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>

-2.85

ⓧ

-0.89

Демографія

-0.73

was

-0.73

 plan

-0.71

WithMany

-0.70

gonic

-0.68

InitStruct

-0.68

is

-0.68

Вид

-0.68

POSITIVE LOGITS

 accla

1.91

 reluct

1.90

 disagre

1.84

 maneu

1.82

 affor

1.81

 increa

1.74

 guarante

1.73

 unwarran

1.73

Juf

1.71

 wherea

1.71

Activations Density 0.887%

references to advertisements and their presence in various contexts

No Comments

No Known Activations