INDEX

Explanations

the word "victory" at varying levels of importance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "victory."

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

 pores

-0.79

ridges

-0.69

UCT

-0.65

asus

-0.65

 notor

-0.65

 abund

-0.64

hemy

-0.62

 livest

-0.61

 suspic

-0.60

 newsletters

-0.60

POSITIVE LOGITS

 victory

0.80

stroke

0.80

 defeat

0.77

hower

0.76

 victories

0.76

antly

0.76

 Lann

0.73

Sham

0.73

bringer

0.72

 defeats

0.69

Activations Density 0.021%

the word "victory" at varying levels of importance

occurrences of the word "victory."

No Comments

No Known Activations