INDEX

Explanations

mentions of different groups or numbers of items in a list

oai_token-act-pair · gpt-3.5-turbo

key elements or metrics in contrasting situations

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

 GOODMAN

-0.98

 Christy

-0.70

 PLUS

-0.69

 Zionism

-0.67

 Brigham

-0.64

 Franz

-0.63

 Regist

-0.62

 Clarks

-0.62

 Redemption

-0.62

 Wrong

-0.61

POSITIVE LOGITS

 others

0.80

Others

0.79

umber

0.74

empl

0.70

aughed

0.69

phthal

0.67

iliary

0.66

 rest

0.65

twe

0.64

thro

0.64

Activations Density 0.218%

mentions of different groups or numbers of items in a list

key elements or metrics in contrasting situations

No Comments

No Known Activations