INDEX

Explanations

phrases related to managing or overseeing tasks and responsibilities

oai_token-act-pair · gpt-3.5-turbo

references to oversight or management responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

estamp

-0.79

IER

-0.70

lier

-0.70

onyms

-0.69

acher

-0.67

reason

-0.67

 guessed

-0.66

Reason

-0.65

osponsors

-0.65

killed

-0.64

POSITIVE LOGITS

 affairs

1.62

 finances

1.48

 operations

1.15

 upkeep

1.10

 activities

1.05

 proceedings

1.00

 preparations

0.99

 rollout

0.97

 operation

0.95

 logistics

0.93

Activations Density 0.351%

phrases related to managing or overseeing tasks and responsibilities

references to oversight or management responsibilities

No Comments

No Known Activations