INDEX

Explanations

verbs or expressions related to recognition, especially regarding actions or behaviors

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setlength

-0.54

Produzione

-0.53

 zanah

-0.50

strix

-0.49

assas

-0.49

ibatkan

-0.48

phur

-0.48

 interessanti

-0.46

Morfologia

-0.46

*)((

-0.46

POSITIVE LOGITS

 acknowledge

1.06

 acknowledging

1.06

 acknowledgment

1.00

 acknowledgement

0.99

 Acknowled

0.99

 acknowledged

0.98

 acknowled

0.93

 Acknowledge

0.92

 acknowledges

0.90

 apprehen

0.88

Activations Density 0.054%

verbs or expressions related to recognition, especially regarding actions or behaviors

No Comments

No Known Activations