INDEX

Explanations

mentions of individuals holding the role of "showrunner" in different contexts

oai_token-act-pair · gpt-3.5-turbo

references to showrunners in television and film contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ī

-0.80

undai

-0.80

 Seym

-0.80

hr

-0.79

ornia

-0.78

ork

-0.76

olk

-0.76

ores

-0.73

romy

-0.72

olia

-0.72

POSITIVE LOGITS

runner

0.98

terson

0.88

runners

0.81

strate

0.75

backer

0.74

ners

0.72

pedia

0.71

luster

0.71

swick

0.68

TAIN

0.67

Activations Density 0.008%

mentions of individuals holding the role of "showrunner" in different contexts

references to showrunners in television and film contexts

No Comments

No Known Activations