INDEX

Explanations

pharmaceutical-related terms or references

oai_token-act-pair · gpt-3.5-turbo

mentions of pharmacies and related entities

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

eer

-1.11

eers

-1.08

cial

-0.94

eering

-0.83

ensis

-0.81

stroke

-0.80

Â¯Â¯Â¯Â¯

-0.79

erers

-0.79

Â¯Â¯

-0.79

bolt

-0.77

POSITIVE LOGITS

adelphia

0.95

ippi

0.73

lectic

0.69

PH

0.69

terday

0.69

aceutical

0.69

Pg

0.68

YS

0.67

osate

0.65

odox

0.64

Activations Density 0.025%

pharmaceutical-related terms or references

mentions of pharmacies and related entities

No Comments

No Known Activations