INDEX

Explanations

words related to leadership positions in sports

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "head" in relation to coaches or leadership roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Suc

-0.74

 subp

-0.66

PsyNetMessage

-0.63

sax

-0.63

 Reincarn

-0.63

 unfocusedRange

-0.62

 Sons

-0.62

terday

-0.62

 mell

-0.62

Mub

-0.61

POSITIVE LOGITS

liners

1.10

hun

1.08

liner

1.07

quarter

1.06

hunter

1.04

lining

1.02

canon

0.98

butt

0.95

quarters

0.93

wind

0.92

Activations Density 0.028%

words related to leadership positions in sports

occurrences of the word "head" in relation to coaches or leadership roles

No Comments

No Known Activations