INDEX

Explanations

terms related to absolute concepts

oai_token-act-pair · gpt-3.5-turbo

references to absence or lack 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cf

-0.62

 Haas

-0.61

 Sass

-0.61

 Gaia

-0.59

 flying

-0.57

spir

-0.57

theless

-0.57

boarding

-0.55

 Franken

-0.54

Das

-0.54

POSITIVE LOGITS

olution

1.50

olute

1.48

urd

1.41

orb

1.38

ence

1.31

olver

1.28

ences

1.26

olve

1.24

olved

1.22

cess

1.22

Activations Density 0.029%

terms related to absolute concepts

references to absence or lack in various contexts

No Comments

No Known Activations