INDEX

Explanations

words related to failure or underperformance

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.57

const

-0.72

put

-0.70

-0.69

EndProject

-0.69

<em>

-0.69

ുറ

-0.68

<strong>

-0.68

//

-0.67

POSITIVE LOGITS

 Minang

2.06

 bandung

2.02

 jaya

1.92

 affor

1.90

 stockholm

1.90

 increa

1.88

 lidl

1.81

 wien

1.79

 impra

1.76

Juf

1.76

Activations Density 0.112%

words related to failure or underperformance

No Comments

No Known Activations