INDEX

Explanations

phrases with double hyphens indicating an interruption or change in thought

oai_token-act-pair · gpt-3.5-turbo

instances of dashes or hyphens used 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.72

 Madden

-0.69

 Galile

-0.68

 cavity

-0.68

fue

-0.67

 dismant

-0.67

 Hass

-0.64

 Mechdragon

-0.63

 substitutes

-0.63

iliary

-0.62

POSITIVE LOGITS

notes

0.96

fuck

0.93

ITS

0.92

sil

0.91

lance

0.88

something

0.88

meaning

0.88

assisted

0.87

multi

0.86

requ

0.85

Activations Density 0.025%

phrases with double hyphens indicating an interruption or change in thought

instances of dashes or hyphens used in the text

No Comments

No Known Activations