INDEX

Explanations

references to the word "Ka" mentioned in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Ka" and its variations, suggesting a focus on a specific subject or entity associated with that term

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

å§«

-0.99

IONS

-0.91

å¤©

-0.83

ROR

-0.80

cream

-0.79

Ö¼

-0.77

ECT

-0.76

OWER

-0.76

flies

-0.76

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.75

POSITIVE LOGITS

iser

0.99

adian

0.97

isers

0.94

pless

0.93

Ka

0.93

pling

0.93

iba

0.91

Ka

0.90

adia

0.90

 Klux

0.89

Activations Density 0.009%

references to the word "Ka" mentioned in various contexts

occurrences of the term "Ka" and its variations, suggesting a focus on a specific subject or entity associated with that term

No Comments

No Known Activations