INDEX

Explanations

mentions of human figures and their interactions in a narrative context

oai_token-act-pair · gpt-3.5-turbo

names and roles of individuals involved in an incident

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

 fulfillment

-0.69

 advertis

-0.69

Quantity

-0.66

hibition

-0.66

 fulfil

-0.65

btn

-0.65

hibit

-0.63

tumblr

-0.63

problem

-0.62

funding

-0.61

POSITIVE LOGITS

 alerted

1.18

 yelled

1.14

 rushed

1.13

 witnessed

1.12

 chased

1.11

 evacuated

1.07

 ejected

1.06

 awoke

1.03

 heard

1.03

 spotted

1.01

Activations Density 0.263%

mentions of human figures and their interactions in a narrative context

names and roles of individuals involved in an incident

No Comments

No Known Activations