INDEX

Explanations

information related to durations expressed in time periods

oai_token-act-pair · gpt-3.5-turbo

phrases related to individuals' milestones and progression in their careers or seasons

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 miscar

-0.73

iots

-0.70

 Ibid

-0.68

 Satanic

-0.63

 Errors

-0.63

insula

-0.63

 duplication

-0.62

 Terrorism

-0.61

 executions

-0.61

 Abuse

-0.61

POSITIVE LOGITS

 ninth

0.83

 undrafted

0.81

 averaging

0.80

 teammates

0.79

 rookie

0.77

 squarely

0.77

 unbeaten

0.76

 rejuven

0.76

ESPN

0.76

 flanked

0.74

Activations Density 0.462%

information related to durations expressed in time periods

phrases related to individuals' milestones and progression in their careers or seasons

No Known Activations