INDEX

Explanations

phrases related to comparisons and differences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the character "âĢ" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Kenyan

-0.65

 blender

-0.64

 Sicily

-0.62

 tremend

-0.62

 whirlwind

-0.62

 dust

-0.61

 scattering

-0.61

 healing

-0.61

 scatter

-0.60

 Bohem

-0.59

POSITIVE LOGITS

alone

0.89

ihad

0.81

¹

0.78

âĹ¼

0.76

thus

0.75

º

0.73

tor

0.72

ership

0.72

ħ

0.72

WER

0.71

Activations Density 0.308%

phrases related to comparisons and differences

occurrences of the character "âĢ" in the text

No Comments

No Known Activations