INDEX

Explanations

proper nouns related to Disney

oai_token-act-pair · gpt-3.5-turbo

references to the name "Walt" and related figures in a specific context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 variance

-0.71

 tampering

-0.69

 elig

-0.63

orescent

-0.62

adesh

-0.61

 aval

-0.61

 linkage

-0.61

Cth

-0.60

RED

-0.59

 extrater

-0.58

POSITIVE LOGITS

 Disney

1.02

 Whitman

1.02

rip

0.98

enthal

0.92

zing

0.89

stad

0.88

 Walt

0.88

pins

0.81

ter

0.81

pin

0.78

Activations Density 0.010%

proper nouns related to Disney

references to the name "Walt" and related figures in a specific context

No Comments

No Known Activations