INDEX

Explanations

words related to actions, processes, or concepts

oai_token-act-pair · gpt-3.5-turbo

gerunds and actions that relate to social, educational, or organizational activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

si

-0.81

ensis

-0.74

word

-0.73

ses

-0.68

bet

-0.68

behind

-0.67

fet

-0.66

shed

-0.66

tes

-0.65

calling

-0.64

POSITIVE LOGITS

 oneself

0.83

redients

0.82

 Yourself

0.74

HAM

0.72

 orphans

0.65

 peoples

0.59

 yourself

0.59

 technologies

0.59

 Efficiency

0.58

 POWER

0.58

Activations Density 0.373%

words related to actions, processes, or concepts

gerunds and actions that relate to social, educational, or organizational activities

No Comments

No Known Activations