INDEX

Explanations

terms related to lists or enumerations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a list or enumeration

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entimes

-0.87

clair

-0.80

ibling

-0.78

lycer

-0.77

xtap

-0.75

ÅĤ

-0.72

OOD

-0.72

ester

-0.70

jad

-0.70

pire

-0.70

POSITIVE LOGITS

 sorts

1.00

 names

0.89

 grievances

0.89

 reasons

0.87

 accomplishments

0.85

 items

0.84

 priorities

0.84

 factors

0.83

 possibilities

0.83

 finalists

0.82

Activations Density 0.087%

terms related to lists or enumerations

phrases indicating a list or enumeration

No Comments

No Known Activations