INDEX

Explanations

mentions of geographic regions such as counties

oai_token-act-pair · gpt-3.5-turbo

references to geographical administrative divisions, particularly counties and villages

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

rawdownloadcloneembedreportprint

-0.69

 agent

-0.65

 procedure

-0.64

PUT

-0.60

 protocol

-0.59

 induction

-0.56

Journal

-0.55

Witness

-0.55

 Protocol

-0.54

OUT

-0.54

POSITIVE LOGITS

hips

1.38

chool

1.16

folk

1.08

hip

1.00

poons

0.99

hare

0.93

pots

0.89

aurus

0.85

peak

0.85

 bordering

0.85

Activations Density 0.094%

mentions of geographic regions such as counties

references to geographical administrative divisions, particularly counties and villages

No Comments

No Known Activations