INDEX

Explanations

action-related words that involve achieving goals or completing tasks

oai_token-act-pair · gpt-3.5-turbo

colloquial references to tasks or challenges related to work and productivity

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

 Neurolog

-0.61

 Zimbabwe

-0.60

 omin

-0.59

ilial

-0.57

 Tanz

-0.57

 valiant

-0.56

ath

-0.54

 treacher

-0.54

 Tracks

-0.54

 hostilities

-0.54

POSITIVE LOGITS

 traction

0.82

 mileage

0.78

osc

0.74

 permission

0.71

 foothold

0.69

 bang

0.68

started

0.67

 ready

0.67

 approval

0.67

ById

0.66

Activations Density 0.326%

action-related words that involve achieving goals or completing tasks

colloquial references to tasks or challenges related to work and productivity

No Comments

No Known Activations