INDEX

Explanations

dates in the format of month followed by day

oai_token-act-pair · gpt-3.5-turbo

specific references to a character or significant element in the context of a series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Attribution

-0.80

 Kimber

-0.68

olver

-0.67

anni

-0.62

Trigger

-0.61

erers

-0.60

Actor

-0.59

 replicate

-0.59

CW

-0.58

 Patterns

-0.58

POSITIVE LOGITS

teenth

0.81

otom

0.78

 peril

0.77

foundland

0.73

otomy

0.68

anamo

0.68

 Gleaming

0.67

Downloadha

0.65

uten

0.65

izen

0.64

Activations Density 0.000%

dates in the format of month followed by day

specific references to a character or significant element in the context of a series

No Comments

No Known Activations