INDEX

Explanations

actions or tasks that are challenging or difficult

oai_token-act-pair · gpt-3.5-turbo

verbs and phrases that indicate difficulty or ease of performing tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ses

-0.69

sis

-0.65

bon

-0.61

 entitled

-0.61

 unspecified

-0.58

 teasp

-0.57

usra

-0.56

=~

-0.55

emonium

-0.54

Jah

-0.53

POSITIVE LOGITS

 oneself

1.22

 nowadays

1.00

 reliably

0.90

 yourself

0.90

 accurately

0.88

due

0.86

 properly

0.83

 correctly

0.80

 anymore

0.80

 efficiently

0.79

Activations Density 0.232%

actions or tasks that are challenging or difficult

verbs and phrases that indicate difficulty or ease of performing tasks

No Comments

No Known Activations