INDEX

Explanations

terms related to strategies or actions used to achieve a specific goal

oai_token-act-pair · gpt-3.5-turbo

mentions of tactics and methods in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.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

leased

-0.74

mbuds

-0.69

omb

-0.69

worthiness

-0.68

league

-0.65

birth

-0.65

vals

-0.64

rake

-0.63

artz

-0.62

odes

-0.61

POSITIVE LOGITS

 tactics

1.08

 tactic

0.89

 tricks

0.86

abwe

0.79

chers

0.74

 guiActiveUn

0.72

 reperto

0.72

 maneuver

0.70

arnaev

0.69

ategy

0.69

Activations Density 0.040%

terms related to strategies or actions used to achieve a specific goal

mentions of tactics and methods in various contexts

No Comments

No Known Activations