INDEX

Explanations

conditional statements referring to future actions or potential outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases expressing hypothetical statements or opinions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 renewal

-0.71

 Resurrection

-0.69

 Waterloo

-0.64

 Advertisement

-0.63

 Bridges

-0.60

 Sources

-0.60

 modernization

-0.60

 srfAttach

-0.60

 widening

-0.59

 unlocks

-0.58

POSITIVE LOGITS

 recognize

1.07

 argue

1.06

 perceive

1.06

 appreciate

1.05

 attest

0.99

 flock

0.99

be

0.99

 complain

0.98

 understandably

0.98

 gladly

0.97

Activations Density 0.175%

conditional statements referring to future actions or potential outcomes

phrases expressing hypothetical statements or opinions

No Known Activations