INDEX

Explanations

legal terms related to offenses and classifications

oai_token-act-pair · gpt-3.5-turbo

classifications and categories related to legal substances and offenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Downloadha

-0.65

campaign

-0.61

natureconservancy

-0.61

 clutch

-0.60

 destro

-0.60

 tort

-0.59

 reproductive

-0.59

 wrench

-0.59

 philos

-0.59

 tack

-0.58

POSITIVE LOGITS

III

1.25

VII

1.14

IV

1.11

XII

1.07

II

1.07

 VIII

1.06

IX

1.01

XI

1.01

 Zero

0.98

0.97

Activations Density 0.090%

legal terms related to offenses and classifications

classifications and categories related to legal substances and offenses

No Comments

No Known Activations