INDEX

Explanations

phrases related to actions or consequences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Champ

-0.66

iris

-0.66

:/

-0.60

neys

-0.59

 actionGroup

-0.55

uyomi

-0.54

glass

-0.54

sonian

-0.53

ãģĨ

-0.53

POSITIVE LOGITS

 turn

1.20

 particular

1.11

 hindsight

1.10

 doing

1.10

 fact

1.04

versely

1.03

 spite

1.00

 retrospect

1.00

 consequence

1.00

efficiency

0.96

Activations Density 0.140%

phrases related to actions or consequences

occurrences of the word "in"

No Comments

No Known Activations