INDEX

Explanations

proper nouns

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 @ 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

 differential

-0.71

 Adin

-0.67

PER

-0.64

 mates

-0.63

 Bravo

-0.62

İĭ

-0.62

ractive

-0.61

ension

-0.60

acter

-0.59

ention

-0.58

POSITIVE LOGITS

igans

1.10

culosis

0.99

igan

0.94

ciating

0.91

gha

0.88

isbury

0.87

cest

0.87

gan

0.87

ãĥĥãĤ¯

0.86

aghan

0.84

Activations Density 0.012%

proper nouns

references to the word "gan" in various contexts

No Comments

No Known Activations