INDEX

Explanations

words related to legal events and political activities

oai_token-act-pair · gpt-3.5-turbo

key political entities and groups involved in various contexts

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

iability

-0.64

 ILCS

-0.63

dig

-0.59

raid

-0.58

 recess

-0.56

tions

-0.56

 compuls

-0.56

ournals

-0.56

respons

-0.53

acion

-0.52

POSITIVE LOGITS

 coincides

1.26

 involves

1.21

 underscores

1.13

 illustrates

1.12

 constitutes

1.10

 differs

1.10

 stems

1.10

 varies

1.10

 indicates

1.08

 amounted

1.08

Activations Density 0.382%

words related to legal events and political activities

key political entities and groups involved in various contexts

No Comments

No Known Activations