INDEX

Explanations

words related to speakers, particularly in a political or public speaking context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "speaker" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urat

-0.75

 Devils

-0.72

 Mines

-0.69

hens

-0.67

 Soldiers

-0.64

arial

-0.60

 annexation

-0.60

thritis

-0.58

iko

-0.58

uilt

-0.57

POSITIVE LOGITS

phone

1.06

hip

0.95

 speaker

0.92

person

0.89

parts

0.89

loo

0.88

glass

0.87

ofer

0.83

boys

0.82

 speakers

0.82

Activations Density 0.056%

words related to speakers, particularly in a political or public speaking context

occurrences of the word "speaker" in various contexts

No Comments

No Known Activations