INDEX

Explanations

words related to factors or influences

oai_token-act-pair · gpt-3.5-turbo

terms related to important factors or contributors 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

phis

-0.80

pit

-0.79

quartered

-0.76

sterdam

-0.75

gem

-0.75

 Parables

-0.75

 Despair

-0.72

irit

-0.69

 tradem

-0.68

dos

-0.68

POSITIVE LOGITS

 factor

1.14

factor

1.06

 factors

0.97

Factor

0.94

 Factor

0.84

imate

0.82

inity

0.81

 Factors

0.79

uates

0.77

uate

0.77

Activations Density 0.011%

words related to factors or influences

terms related to important factors or contributors in various contexts

No Comments

No Known Activations