INDEX

Explanations

instances where something is being forgotten or ignored

oai_token-act-pair · gpt-3.5-turbo

instances of the word "forget" and its variations

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

XY

-0.70

amen

-0.69

tained

-0.69

Parser

-0.69

 nomine

-0.68

 coefficients

-0.68

arte

-0.68

inals

-0.67

uana

-0.67

ullivan

-0.65

POSITIVE LOGITS

fulness

1.15

fully

0.99

ful

0.98

theless

0.91

 forgetting

0.84

 forgot

0.83

 forget

0.83

remember

0.79

 remembered

0.78

ingly

0.77

Activations Density 0.020%

instances where something is being forgotten or ignored

instances of the word "forget" and its variations

No Comments

No Known Activations