INDEX

Explanations

instances of unusual or out-of-context words or phrases

oai_token-act-pair · gpt-3.5-turbo

significant events or actions in a narrative context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Ħ¢

-0.75

uster

-0.59

 manif

-0.57

 gaining

-0.56

 outp

-0.54

 quadru

-0.54

 extrater

-0.54

').

-0.54

ŃĶ

-0.53

 risen

-0.53

POSITIVE LOGITS

↵

1.16

<|endoftext|>

0.95

↵↵

0.84

SPONSORED

0.82

 CrossRef

0.76

argo

0.69

alia

0.62

PNG

0.62

âĺ

0.61

 âĶľâĶĢâĶĢ

0.60

Activations Density 0.251%

instances of unusual or out-of-context words or phrases

significant events or actions in a narrative context

No Comments

No Known Activations