INDEX

Explanations

names of specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

references to specific characters or entities, particularly in storytelling contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ¼ãĥĨ

-0.75

 Pathfinder

-0.75

é¾įåĸļå£«

-0.69

 inaccur

-0.64

éĹ

-0.64

 sequ

-0.63

 reflecting

-0.62

 sarc

-0.62

 penetration

-0.61

 Barnett

-0.61

POSITIVE LOGITS

nea

1.08

iety

1.00

pped

0.99

cho

0.96

ving

0.95

ear

0.93

agh

0.93

enhagen

0.93

ther

0.91

etooth

0.89

Activations Density 0.066%

names of specific individuals or entities

references to specific characters or entities, particularly in storytelling contexts

No Comments

No Known Activations