INDEX

Explanations

second person pronouns followed by actions or descriptions

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>

-1.24

 spek

-0.85

 makro

-0.75

 saus

-0.73

kog

-0.72

 truk

-0.71

 behar

-0.71

 augus

-0.68

 sava

-0.67

 gero

-0.67

POSITIVE LOGITS

 Thou

1.12

THY

1.08

Thy

1.06

 thou

1.03

Thou

1.03

thy

1.00

 pylab

0.95

Thy

0.93

 dévou

0.91

 sympy

0.90

Activations Density 0.334%

second person pronouns followed by actions or descriptions

No Comments

No Known Activations