INDEX

Explanations

words related to geographical locations or specific places

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ast" in various contexts

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

yip

-0.85

senal

-0.80

pared

-0.79

alties

-0.78

perty

-0.77

pheus

-0.76

mercial

-0.74

ptive

-0.74

pton

-0.74

chy

-0.74

POSITIVE LOGITS

rophe

1.04

roph

0.94

rophic

0.92

ruct

0.92

ream

0.85

efully

0.85

rup

0.84

hest

0.84

roid

0.84

rop

0.84

Activations Density 0.017%

words related to geographical locations or specific places

occurrences of the word "ast" in various contexts

No Comments

No Known Activations