INDEX

Explanations

words related to job positions or roles

oai_token-act-pair · gpt-3.5-turbo

references to specific roles or positions in a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vous

-0.80

Interstitial

-0.78

 Warn

-0.78

cause

-0.68

bey

-0.67

Jane

-0.66

isks

-0.65

actionDate

-0.63

ignore

-0.61

 Collect

-0.60

POSITIVE LOGITS

 positions

0.95

 position

0.90

 vacated

0.87

atile

0.83

 roles

0.80

ngth

0.75

 positional

0.75

 assignments

0.74

 orientation

0.73

ession

0.72

Activations Density 0.042%

words related to job positions or roles

references to specific roles or positions in a sports context

No Comments

No Known Activations