INDEX

Explanations

terms related to sports teams and their activities

oai_token-act-pair · gpt-3.5-turbo

references to sports teams and their related aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vasive

-0.66

 Blumenthal

-0.66

romy

-0.64

Pic

-0.64

 stalk

-0.64

croft

-0.61

Reuters

-0.61

Tube

-0.61

igmat

-0.59

 Signs

-0.59

POSITIVE LOGITS

 coaches

0.77

akeru

0.77

hesion

0.72

orses

0.71

issors

0.71

 relegation

0.68

iets

0.67

 preseason

0.66

 Plays

0.64

 scouts

0.64

Activations Density 0.526%

terms related to sports teams and their activities

references to sports teams and their related aspects

No Comments

No Known Activations