INDEX

Explanations

mentions of actions or scenarios related to competition, leveling, or development

oai_token-act-pair · gpt-3.5-turbo

terms related to activities and processes involving interaction or engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

redo

-0.84

heric

-0.73

ython

-0.72

ses

-0.71

inately

-0.69

idal

-0.69

cci

-0.69

assad

-0.68

Ĥª

-0.68

sy

-0.68

POSITIVE LOGITS

 spree

1.09

redients

0.93

 ability

0.89

tons

0.88

 mechanism

0.82

 prowess

0.81

 frenzy

0.80

 habits

0.80

rights

0.77

 process

0.75

Activations Density 0.362%

mentions of actions or scenarios related to competition, leveling, or development

terms related to activities and processes involving interaction or engagement

No Comments

No Known Activations