INDEX

Explanations

phrases indicating continuity or progression in a narrative

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "along."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cit

-0.64

oan

-0.63

agara

-0.62

NAS

-0.61

abuse

-0.59

yg

-0.58

 liable

-0.58

ns

-0.58

acs

-0.58

oa

-0.57

POSITIVE LOGITS

along

0.79

 Paso

0.76

side

0.74

 along

0.71

wagon

0.68

 Vald

0.66

 Admir

0.65

oit

0.64

||||

0.63

edIn

0.62

Activations Density 0.018%

phrases indicating continuity or progression in a narrative

occurrences of the word "along."

No Comments

No Known Activations