INDEX

Explanations

phrases or words mentioning stories or recounts

oai_token-act-pair · gpt-3.5-turbo

references to various narratives or accounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arius

-0.80

atur

-0.65

ugal

-0.65

 Plasma

-0.64

activated

-0.64

aband

-0.63

atum

-0.61

cation

-0.61

 Processor

-0.60

Ã©e

-0.60

POSITIVE LOGITS

 stories

3.65

stories

2.87

 tales

2.83

 Stories

2.65

 story

2.32

 narratives

2.13

 anecdotes

2.06

 storylines

2.03

story

1.86

 tale

1.82

Activations Density 0.027%

phrases or words mentioning stories or recounts

references to various narratives or accounts

No Comments

No Known Activations