INDEX

Explanations

references to policies and policy-related discussions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 captcha

-0.79

ITNESS

-0.76

cause

-0.74

WAY

-0.74

 colours

-0.72

 organise

-0.69

mind

-0.67

RGB

-0.67

ãĤ¨ãĥ«

-0.67

 racists

-0.63

POSITIVE LOGITS

 Analyst

0.86

artisan

0.81

edia

0.80

Brook

0.80

Mic

0.78

 Analysis

0.76

 Insight

0.74

 Advisor

0.73

 Strategies

0.72

rief

0.72

Activations Density 0.032%

references to policies and policy-related discussions

No Comments

No Known Activations