INDEX

Explanations

terms related to inclusion and coverage

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce lists or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĥ¼ãĥ³

-0.83

ortun

-0.80

izens

-0.78

ossal

-0.77

ocrats

-0.77

psons

-0.71

iny

-0.71

oled

-0.68

rift

-0.68

ocity

-0.68

POSITIVE LOGITS

:-

0.97

 lowering

0.90

 pacing

0.89

 avoiding

0.89

 preventing

0.87

 ensuring

0.87

 removing

0.85

 reducing

0.85

 attendance

0.83

 providing

0.82

Activations Density 0.163%

terms related to inclusion and coverage

phrases that introduce lists or examples

No Comments

No Known Activations