INDEX

Explanations

the word "again" and variations of it in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "again."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ariat

-0.60

 summary

-0.57

 newcomers

-0.57

 collective

-0.57

 nodes

-0.56

aucus

-0.55

 multitude

-0.55

 privilege

-0.54

ometric

-0.54

 delegation

-0.54

POSITIVE LOGITS

eday

0.83

nir

0.82

abouts

0.82

nces

0.81

mort

0.77

luaj

0.75

swick

0.72

âĺ

0.71

 tomorrow

0.70

castle

0.69

Activations Density 0.049%

the word "again" and variations of it in different contexts

instances of the word "again."

No Comments

No Known Activations