INDEX

Explanations

mentions of bus-related activities or locations

oai_token-act-pair · gpt-3.5-turbo

mentions of buses 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 marrow

-0.75

 Martial

-0.73

 Centauri

-0.66

 accur

-0.66

aneous

-0.64

 limb

-0.64

sson

-0.61

 negatives

-0.61

theless

-0.61

 Christensen

-0.60

POSITIVE LOGITS

loads

1.25

load

1.11

boys

0.99

INESS

0.95

hel

0.92

kers

0.89

boy

0.87

hy

0.86

inson

0.82

hell

0.79

Activations Density 0.019%

mentions of bus-related activities or locations

mentions of buses in various contexts

No Comments

No Known Activations