INDEX

Explanations

phrases related to cutting or severing

oai_token-act-pair · gpt-3.5-turbo

the word "cut" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 merits

-0.70

Ort

-0.66

 Phill

-0.65

 resilience

-0.64

Luc

-0.63

 goodwill

-0.62

 shares

-0.61

 persever

-0.61

 Lynd

-0.60

 Ples

-0.60

POSITIVE LOGITS

cut

4.44

cuts

3.04

cutting

2.19

Cut

2.10

Cut

1.81

cut

1.69

 cutter

1.42

 Cutting

1.33

 cuts

1.32

 Cutter

1.22

Activations Density 0.006%

phrases related to cutting or severing

the word "cut" and its variations in different contexts

No Comments

No Known Activations