INDEX

Explanations

comparisons or evaluations between different levels or instances of things

oai_token-act-pair · gpt-3.5-turbo

comparative adjectives and their intensifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aren

-0.78

follow

-0.69

ä¸ī

-0.69

çľ

-0.66

iland

-0.66

ni

-0.66

EP

-0.66

ierrez

-0.65

çĽ

-0.65

mad

-0.65

POSITIVE LOGITS

 part

0.89

 your

0.85

 portion

0.85

 portions

0.77

you

0.76

the

0.73

liest

0.72

 they

0.69

 question

0.69

 side

0.68

Activations Density 0.041%

comparisons or evaluations between different levels or instances of things

comparative adjectives and their intensifiers

No Comments

No Known Activations