INDEX

Explanations

instances of the word "avoid" followed by a number indicating the strength of the match

oai_token-act-pair · gpt-3.5-turbo

instances of the word "avoid" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iop

-0.81

geist

-0.80

Rated

-0.76

cart

-0.73

BILL

-0.67

Led

-0.65

Hour

-0.65

timer

-0.65

quartered

-0.64

rooms

-0.63

POSITIVE LOGITS

 pitfalls

0.85

 detection

0.83

 wasting

0.75

 distractions

0.74

ably

0.70

 answering

0.69

 smoking

0.68

 altogether

0.68

vana

0.66

 avoidance

0.66

Activations Density 0.040%

instances of the word "avoid" followed by a number indicating the strength of the match

instances of the word "avoid" in various contexts

No Comments

No Known Activations