INDEX

Explanations

words related to exciting and risky activities or scenarios

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "adventure" and its variations

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

iths

-0.79

itionally

-0.77

ongyang

-0.77

enser

-0.76

heed

-0.76

iple

-0.75

animous

-0.75

ivari

-0.72

creen

-0.72

uctor

-0.70

POSITIVE LOGITS

Adventure

0.90

 Adventure

0.88

 Wander

0.84

rs

0.84

 awaits

0.83

 Adventures

0.81

nels

0.81

 Phant

0.79

 Afric

0.77

 Journey

0.76

Activations Density 0.025%

words related to exciting and risky activities or scenarios

occurrences of the word "adventure" and its variations

No Comments

No Known Activations