INDEX

Explanations

statements or responses in a conversation

oai_token-act-pair · gpt-3.5-turbo

phrases that express approval or affirmation

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

 consolidation

-0.82

 synerg

-0.79

 neighb

-0.75

 hemor

-0.71

 targeted

-0.70

 clones

-0.70

ulators

-0.69

 allied

-0.69

 artif

-0.69

 controllers

-0.68

POSITIVE LOGITS

âĶĢâĶĢâĶĢâĶĢ

1.19

âĶĢâĶĢ

1.13

Okay

1.02

 Alright

1.01

Hey

0.98

Alright

0.97

cffffcc

0.93

ï¸ı

0.92

hello

0.92

Damn

0.91

Activations Density 0.163%

statements or responses in a conversation

phrases that express approval or affirmation

No Comments

No Known Activations