INDEX

Explanations

instances where someone is mentioned performing an action

oai_token-act-pair · gpt-3.5-turbo

verbs that indicate actions or statements made by individuals

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

 guiActiveUnfocused

-0.76

 Arrow

-0.71

'>

-0.65

antics

-0.63

nings

-0.62

plementation

-0.62

hern

-0.61

urers

-0.61

ravel

-0.60

 unbeliev

-0.60

POSITIVE LOGITS

 herself

0.77

 himself

0.75

ilyn

0.65

aciously

0.65

 passionately

0.65

osaurus

0.61

©¶æ¥µ

0.61

vae

0.59

UTC

0.58

 filib

0.57

Activations Density 0.408%

instances where someone is mentioned performing an action

verbs that indicate actions or statements made by individuals

No Comments

No Known Activations