INDEX

Explanations

words related to negative impact or harm

oai_token-act-pair · gpt-3.5-turbo

terms related to negative impacts and challenges 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 @ 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

iverse

-0.70

Aly

-0.70

 Wonderland

-0.69

DOE

-0.65

 Cosmos

-0.65

 Milky

-0.65

 brightly

-0.65

Cah

-0.65

 Gaia

-0.64

 Atlantis

-0.63

POSITIVE LOGITS

(>

1.05

clerosis

0.79

andowski

0.76

ãĥķãĤ¡

0.72

ographical

0.71

smanship

0.68

oldown

0.68

unctions

0.67

secution

0.66

rosis

0.66

Activations Density 0.483%

words related to negative impact or harm

terms related to negative impacts and challenges in various contexts

No Comments

No Known Activations