INDEX

Explanations

personal development or self-improvement advice

oai_token-act-pair · gpt-3.5-turbo

instances of the word "let's" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

ELD

-0.64

 Slug

-0.63

 aids

-0.58

 Contributions

-0.58

 Source

-0.57

 Gardens

-0.57

 Able

-0.57

 Associated

-0.56

 Deaths

-0.55

 Hours

-0.55

POSITIVE LOGITS

 assume

0.98

 clarify

0.96

 pretend

0.92

 summarize

0.91

 proceed

0.91

 denote

0.90

 resolve

0.89

 simplify

0.89

 illustrate

0.88

 emphasize

0.88

Activations Density 0.015%

personal development or self-improvement advice

instances of the word "let's" and its variations

No Comments

No Known Activations