INDEX

Explanations

food ingredients, particularly beans and various vegetables like onions, peppers, and almonds

oai_token-act-pair · gpt-3.5-turbo

references to beans and related food ingredients

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

 maneuvers

-0.77

minist

-0.70

ctor

-0.67

pmwiki

-0.66

Student

-0.64

Witness

-0.64

 practition

-0.60

crime

-0.60

 circumstance

-0.59

 defect

-0.59

POSITIVE LOGITS

kins

1.19

ynthesis

1.12

pring

1.08

heet

1.06

hips

1.04

aurus

1.02

poons

0.99

creen

0.97

cale

0.96

mith

0.96

Activations Density 0.096%

food ingredients, particularly beans and various vegetables like onions, peppers, and almonds

references to beans and related food ingredients

No Comments

No Known Activations