INDEX

Explanations

words beginning with 'c' followed by a number, possibly related to coded actions or commands

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "c"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 GOODMAN

-0.94

ãĥĹ

-0.74

tenance

-0.71

å§«

-0.69

 Tinder

-0.67

 favourites

-0.67

 warr

-0.66

é¾įå

-0.66

 Sachs

-0.64

éĹĺ

-0.63

POSITIVE LOGITS

rosso

1.25

ologne

1.19

rescent

1.17

ogs

1.13

ordon

1.13

rows

1.11

abb

1.08

oder

1.07

uffed

1.07

umb

1.06

Activations Density 0.026%

words beginning with 'c' followed by a number, possibly related to coded actions or commands

occurrences of the letter "c"

No Comments

No Known Activations