INDEX

Explanations

information related to the subsequent actions or outcomes of different entities or individuals

oai_token-act-pair · gpt-3.5-turbo

descriptions of significant events or achievements in a person's life or career

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

terday

-0.99

Answer

-0.75

 Yesterday

-0.75

 POLITICO

-0.72

Leaks

-0.70

(@

-0.66

 Prediction

-0.64

Yesterday

-0.63

é¾įå¥ĳå£«

-0.63

HUD

-0.63

POSITIVE LOGITS

 thereafter

1.06

 stint

1.00

 subsequent

0.98

 later

0.94

lived

0.94

sequently

0.94

 unsuccessful

0.93

 eventually

0.91

 prolific

0.90

 career

0.90

Activations Density 0.777%

information related to the subsequent actions or outcomes of different entities or individuals

descriptions of significant events or achievements in a person's life or career

No Comments

No Known Activations