INDEX

Explanations

instances of the word "write" or related words like "writing" or "written."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "write" and its variations indicating acts of writing

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

Ĭ±

-0.89

agara

-0.77

abe

-0.73

azar

-0.73

EGA

-0.71

 Ukrain

-0.71

ega

-0.67

imation

-0.66

 Unsure

-0.66

allows

-0.65

POSITIVE LOGITS

 poems

0.90

writing

0.87

smanship

0.87

writer

0.85

acters

0.82

 poetry

0.77

writers

0.76

 poem

0.76

 essays

0.76

itatively

0.75

Activations Density 0.047%

instances of the word "write" or related words like "writing" or "written."

occurrences of the word "write" and its variations indicating acts of writing

No Comments

No Known Activations