INDEX

Explanations

mentions of the soccer club Tottenham

oai_token-act-pair · gpt-3.5-turbo

references to the football club Tottenham

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

xon

-0.94

phe

-0.74

ppo

-0.73

lly

-0.71

 Franken

-0.70

ysis

-0.70

cision

-0.69

ocobo

-0.67

carry

-0.67

sbm

-0.66

POSITIVE LOGITS

 Hots

2.06

ottenham

0.84

rament

0.83

ieth

0.83

 Tottenham

0.78

 Rapids

0.77

ites

0.77

bledon

0.75

wick

0.74

 unden

0.72

Activations Density 0.011%

mentions of the soccer club Tottenham

references to the football club Tottenham

No Comments

No Known Activations