INDEX

Explanations

occurrences of the word "gan."

oai_token-act-pair · gpt-3.5-turbo

references to the word "gan" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 differential

-0.69

İĭ

-0.68

 Adin

-0.68

ension

-0.67

ractive

-0.64

ensions

-0.63

 mates

-0.63

ention

-0.61

 pupils

-0.60

Reference

-0.60

POSITIVE LOGITS

igans

1.20

culosis

1.03

igan

1.01

cia

0.94

ciating

0.93

gha

0.93

gan

0.93

uclear

0.85

non

0.85

aghan

0.85

Activations Density 0.029%

occurrences of the word "gan."

references to the word "gan" in various contexts

No Comments

No Known Activations